gguf

[kmnnmk212-source]

https://github.com/leejet/stable-diffusion.cpp/blob/master/docs/hidream_o1_image.md

!./bin/sd-cli -m /content/ComfyUI/models/diffusion_models/hidream-i1-fast-Q5_0.gguf -p "a lovely cat holding a sign says" --cfg-scale 1.0 -v -H 1024 -W 1024

[DEBUG] main.cpp:547 - version: stable-diffusion.cpp version master-585-44cca3d, commit 44cca3d
[DEBUG] main.cpp:548 - System Info:
SSE3 = 1 | AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | VSX = 0 |
[DEBUG] main.cpp:549 - SDCliParams {
mode: img_gen,
output_path: "output.png",
image_path: "",
metadata_format: "text",
verbose: true,
color: false,
canny_preprocess: false,
convert_name: false,
preview_method: none,
preview_interval: 1,
preview_path: "preview.png",
preview_fps: 16,
taesd_preview: false,
preview_noisy: false,
metadata_raw: false,
metadata_brief: false,
metadata_all: false
}
[DEBUG] main.cpp:550 - SDContextParams {
n_threads: 2,
model_path: "/content/ComfyUI/models/diffusion_models/hidream-i1-fast-Q5_0.gguf",
clip_l_path: "",
clip_g_path: "",
clip_vision_path: "",
t5xxl_path: "",
llm_path: "",
llm_vision_path: "",
diffusion_model_path: "",
high_noise_diffusion_model_path: "",
vae_path: "",
taesd_path: "",
esrgan_path: "",
control_net_path: "",
embedding_dir: "",
embeddings: {
}
wtype: NONE,
tensor_type_rules: "",
lora_model_dir: ".",
photo_maker_path: "",
rng_type: cuda,
sampler_rng_type: NONE,
offload_params_to_cpu: false,
enable_mmap: false,
control_net_cpu: false,
clip_on_cpu: false,
vae_on_cpu: false,
flash_attn: false,
diffusion_flash_attn: false,
diffusion_conv_direct: false,
vae_conv_direct: false,
circular: false,
circular_x: false,
circular_y: false,
chroma_use_dit_mask: true,
qwen_image_zero_cond_t: false,
chroma_use_t5_mask: false,
chroma_t5_mask_pad: 1,
prediction: NONE,
lora_apply_mode: auto,
force_sdxl_vae_conv_scale: false
}
[DEBUG] main.cpp:551 - SDGenerationParams {
loras: "{
}",
high_noise_loras: "{
}",
prompt: "a lovely cat holding a sign says",
negative_prompt: "",
clip_skip: -1,
width: 1024,
height: 1024,
batch_count: 1,
init_image_path: "",
end_image_path: "",
mask_image_path: "",
control_image_path: "",
ref_image_paths: [],
control_video_path: "",
auto_resize_ref_image: true,
increase_ref_index: false,
pm_id_images_dir: "",
pm_id_embed_path: "",
pm_style_strength: 20,
skip_layers: [7, 8, 9],
sample_params: (txt_cfg: 1.00, img_cfg: 1.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 20, eta: inf, shifted_timestep: 0, flow_shift: inf),
high_noise_skip_layers: [7, 8, 9],
high_noise_sample_params: (txt_cfg: 7.00, img_cfg: 7.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 20, eta: inf, shifted_timestep: 0, flow_shift: inf),
custom_sigmas: [],
cache_mode: "",
cache_option: "",
cache: disabled (threshold=inf, start=0.15, end=0.95),
moe_boundary: 0.875,
video_frames: 1,
fps: 16,
vace_strength: 1,
strength: 0.75,
control_strength: 0.9,
seed: 42,
upscale_repeats: 1,
upscale_tile_size: 128,
vae_tiling_params: { 0, 0, 0, 0.5, 0, 0 },
}
[DEBUG] stable-diffusion.cpp:175 - Using CUDA backend
[INFO ] ggml_extend.hpp:81 - ggml_cuda_init: found 1 CUDA devices (Total VRAM: 14912 MiB):
[INFO ] ggml_extend.hpp:81 - Device 0: Tesla T4, compute capability 7.5, VMM: yes, VRAM: 14912 MiB
[INFO ] stable-diffusion.cpp:262 - loading model from '/content/ComfyUI/models/diffusion_models/hidream-i1-fast-Q5_0.gguf'
[INFO ] model.cpp:229 - load /content/ComfyUI/models/diffusion_models/hidream-i1-fast-Q5_0.gguf using gguf format
[DEBUG] model.cpp:278 - init from '/content/ComfyUI/models/diffusion_models/hidream-i1-fast-Q5_0.gguf'
[ERROR] stable-diffusion.cpp:349 - get sd version from file failed: '/content/ComfyUI/models/diffusion_models/hidream-i1-fast-Q5_0.gguf'
[INFO ] main.cpp:703 - new_sd_ctx_t failed

[wbruna]

master-585-44cca3d

First, HiDream o1 support was added in master-602-0665a7f, a few weeks after the version you are testing.

Also, "HiDream o1" and "HiDream i1" are different models. Only the former is supported right now.

[kmnnmk212-source]

!./build/bin/sd-cli
-m /content/hidream_o1_image_fp8_scaled.safetensors
-p "a lovely cat"
-H 512 -W 512
--steps 11
--cfg-scale 3.0
--vae-on-cpu
--clip-on-cpu
--max-vram 13
-t 2
--sampling-method euler_a
--scheduler discrete
-o output.png

[INFO ] ggml_extend.hpp:63 - ggml_cuda_init: found 1 CUDA devices (Total VRAM: 14912 MiB):
[INFO ] ggml_extend.hpp:63 - Device 0: Tesla T4, compute capability 7.5, VMM: yes, VRAM: 14912 MiB
[INFO ] stable-diffusion.cpp:216 - loading model from '/content/hidream_o1_image_fp8_scaled.safetensors'
[INFO ] model.cpp:219 - load /content/hidream_o1_image_fp8_scaled.safetensors using safetensors format
[INFO ] stable-diffusion.cpp:309 - Version: HiDream O1
[INFO ] stable-diffusion.cpp:337 - Weight type stat: f32: 368 | f16: 368 | bf16: 372
[INFO ] stable-diffusion.cpp:338 - Conditioner weight type stat:
[INFO ] stable-diffusion.cpp:339 - Diffusion model weight type stat:
[INFO ] stable-diffusion.cpp:340 - VAE weight type stat:
[INFO ] stable-diffusion.cpp:436 - CLIP: Using CPU backend
[INFO ] stable-diffusion.cpp:622 - VAE Autoencoder: Using CPU backend
[INFO ] stable-diffusion.cpp:684 - using FakeVAE
[ERROR] ggml_extend.hpp:2738 - fake_vae alloc params backend buffer failed, num_tensors = 0
[INFO ] model.cpp:795 - NOT using mmap for '/content/hidream_o1_image_fp8_scaled.safetensors' (mmap disabled by caller)
[INFO ] model.cpp:807 - model files processing completed in 0.00s
|> | 1/1108 - 0.00MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.final_layer2.linear.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 4/1108 - 0.03MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.embed_tokens.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 7/1108 - 14.94MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 9/1108 - 37.37MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 11/1108 - 48.96MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 15/1108 - 64.85MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 17/1108 - 61.41MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 20/1108 - 62.71MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 25/1108 - 54.35MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 27/1108 - 52.95MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 29/1108 - 53.99MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 35/1108 - 61.34MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 38/1108 - 61.98MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 40/1108 - 62.57MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 43/1108 - 55.77MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 45/1108 - 57.73MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 47/1108 - 57.94MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 53/1108 - 61.29MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 56/1108 - 60.34MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 61/1108 - 56.29MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 63/1108 - 53.57MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 65/1108 - 55.81MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 69/1108 - 104.23MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 71/1108 - 102.84MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 76/1108 - 106.34MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 81/1108 - 101.41MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 89/1108 - 105.76MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 92/1108 - 105.39MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 99/1108 - 102.85MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 107/1108 - 108.14MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 110/1108 - 106.36MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 112/1108 - 106.02MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 117/1108 - 104.01MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 123/1108 - 108.53MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 125/1108 - 107.47MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 128/1108 - 107.14MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 130/1108 - 106.83MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 135/1108 - 104.96MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 141/1108 - 109.07MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 143/1108 - 108.11MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 146/1108 - 107.80MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 151/1108 - 107.72MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 153/1108 - 105.76MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======> | 161/1108 - 108.64MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======> | 164/1108 - 108.36MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======> | 171/1108 - 106.45MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 179/1108 - 109.09MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 182/1108 - 108.83MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 189/1108 - 107.01MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 191/1108 - 108.17MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 197/1108 - 108.54MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 200/1108 - 106.49MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 207/1108 - 104.11MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 213/1108 - 107.07MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 215/1108 - 105.56MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 218/1108 - 105.36MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 225/1108 - 103.97MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 233/1108 - 106.09MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 236/1108 - 105.90MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 241/1108 - 105.86MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 243/1108 - 105.31MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 245/1108 - 106.24MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 251/1108 - 107.31MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 254/1108 - 107.12MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 256/1108 - 106.93MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 261/1108 - 105.81MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 267/1108 - 108.28MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 269/1108 - 107.70MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 272/1108 - 107.52MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 274/1108 - 107.35MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 279/1108 - 106.27MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 285/1108 - 108.61MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 287/1108 - 108.05MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 290/1108 - 107.88MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 292/1108 - 107.71MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 297/1108 - 106.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 305/1108 - 108.37MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 308/1108 - 108.20MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 313/1108 - 108.15MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 315/1108 - 107.66MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 317/1108 - 108.42MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 323/1108 - 109.28MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 326/1108 - 108.50MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 333/1108 - 107.37MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 336/1108 - 109.40MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 341/1108 - 108.33MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 344/1108 - 107.03MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 351/1108 - 104.92MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================> | 359/1108 - 106.39MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================> | 362/1108 - 105.72MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================> | 369/1108 - 104.79MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 377/1108 - 106.19MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 380/1108 - 106.07MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 387/1108 - 105.66MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 393/1108 - 107.42MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 395/1108 - 107.01MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 398/1108 - 106.88MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 400/1108 - 106.76MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 405/1108 - 105.99MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 413/1108 - 107.29MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 416/1108 - 107.17MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 421/1108 - 107.13MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 423/1108 - 106.30MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 431/1108 - 107.55MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 434/1108 - 107.43MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 439/1108 - 107.40MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 441/1108 - 107.04MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 443/1108 - 107.61MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 449/1108 - 107.79MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 452/1108 - 107.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 459/1108 - 107.29MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 465/1108 - 108.82MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 467/1108 - 108.45MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 470/1108 - 108.34MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 472/1108 - 108.22MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 477/1108 - 106.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 483/1108 - 108.15MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 485/1108 - 107.37MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 488/1108 - 106.85MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 495/1108 - 105.29MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 503/1108 - 106.38MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 506/1108 - 106.28MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 511/1108 - 106.25MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 513/1108 - 105.57MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 521/1108 - 106.61MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 524/1108 - 106.52MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 531/1108 - 105.82MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 539/1108 - 106.84MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 542/1108 - 106.74MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 547/1108 - 106.72MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 549/1108 - 106.44MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 551/1108 - 106.90MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 557/1108 - 107.43MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 560/1108 - 107.33MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 562/1108 - 107.24MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 567/1108 - 106.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 573/1108 - 107.92MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 575/1108 - 107.62MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 578/1108 - 107.53MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 580/1108 - 107.44MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 585/1108 - 106.88MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 591/1108 - 108.10MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 593/1108 - 107.81MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 596/1108 - 107.72MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 601/1108 - 107.70MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 603/1108 - 107.08MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 611/1108 - 107.99MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 614/1108 - 107.90MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 621/1108 - 106.60MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 623/1108 - 107.01MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 629/1108 - 106.83MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 632/1108 - 106.42MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 637/1108 - 107.07MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 639/1108 - 105.51MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 641/1108 - 105.91MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============================> | 647/1108 - 106.37MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============================> | 650/1108 - 105.97MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.t_embedder1.mlp.0.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.t_embedder1.mlp.2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============================> | 665/1108 - 106.70MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============================> | 684/1108 - 106.83MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================================> | 713/1108 - 106.88MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================================> | 742/1108 - 106.97MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================================> | 764/1108 - 106.96MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================================> | 796/1108 - 107.07MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================================> | 815/1108 - 107.02MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================================> | 847/1108 - 107.14MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================================> | 876/1108 - 107.19MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================================> | 905/1108 - 107.23MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================================> | 927/1108 - 107.26MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================================> | 959/1108 - 107.36MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================================> | 988/1108 - 107.42MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============================================> | 1020/1108 - 107.53MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============================================> | 1046/1108 - 107.55MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================================================> | 1068/1108 - 107.53MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.merger.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================================================| 1097/1108 - 107.32MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.merger.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.x_embedder.proj1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.x_embedder.proj2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================================================| 1108/1108 - 107.72MB/s
[INFO ] model.cpp:1135 - loading tensors completed, taking 71.42s (read: 21.10s, memcpy: 0.00s, convert: 46.81s, copy_to_backend: 2.25s)
[INFO ] stable-diffusion.cpp:945 - total params memory size = 15383.85MB (VRAM 14508.23MB, RAM 875.61MB): text_encoders 875.61MB(RAM), diffusion_model 14508.23MB(VRAM), vae 0.00MB(RAM), controlnet 0.00MB(VRAM), pmid 0.00MB(RAM)
[INFO ] stable-diffusion.cpp:1030 - running in FLOW mode
[INFO ] stable-diffusion.cpp:3503 - generate_image 512x512
[INFO ] denoiser.hpp:500 - get_sigmas with discrete scheduler
[INFO ] stable-diffusion.cpp:2947 - sampling using Euler A method
[INFO ] stable-diffusion.cpp:3304 - get_learned_condition completed, taking 0.00s
[INFO ] stable-diffusion.cpp:3537 - generating image: 1/1 - seed 42
|==================================================| 11/11 - 1.01s/it
[INFO ] stable-diffusion.cpp:3569 - sampling completed, taking 11.49s
[INFO ] stable-diffusion.cpp:3587 - generating 1 latent images completed, taking 11.50s
[INFO ] stable-diffusion.cpp:3328 - decoding 1 latents
[INFO ] stable-diffusion.cpp:3344 - latent 1 decoded, taking 0.00s
[INFO ] stable-diffusion.cpp:3348 - decode_first_stage completed, taking 0.00s
[INFO ] stable-diffusion.cpp:3729 - generate_image completed in 11.55s
[INFO ] main.cpp:441 - save result image 0 to 'output.png' (success)
[INFO ] main.cpp:490 - 1/1 images saved

The image is blank.

[kmnnmk212-source]

colab t4
Are there settings for creating a clear image?

[kmnnmk212-source]

!./build/bin/sd-cli
-m /content/hidream_o1_image_dev_fp8_scaled.safetensors
-p "cat"
-H 512 -W 512
--steps 20
--cfg-scale 3.0
--vae-on-cpu
--clip-on-cpu
--max-vram 13
-t 2
-o output.png

[INFO ] ggml_extend.hpp:63 - ggml_cuda_init: found 1 CUDA devices (Total VRAM: 14912 MiB):
[INFO ] ggml_extend.hpp:63 - Device 0: Tesla T4, compute capability 7.5, VMM: yes, VRAM: 14912 MiB
[INFO ] stable-diffusion.cpp:216 - loading model from '/content/hidream_o1_image_dev_fp8_scaled.safetensors'
[INFO ] model.cpp:219 - load /content/hidream_o1_image_dev_fp8_scaled.safetensors using safetensors format
[INFO ] stable-diffusion.cpp:309 - Version: HiDream O1
[INFO ] stable-diffusion.cpp:337 - Weight type stat: f32: 368 | f16: 368 | bf16: 372
[INFO ] stable-diffusion.cpp:338 - Conditioner weight type stat:
[INFO ] stable-diffusion.cpp:339 - Diffusion model weight type stat:
[INFO ] stable-diffusion.cpp:340 - VAE weight type stat:
[INFO ] stable-diffusion.cpp:436 - CLIP: Using CPU backend
[INFO ] stable-diffusion.cpp:622 - VAE Autoencoder: Using CPU backend
[INFO ] stable-diffusion.cpp:684 - using FakeVAE
[ERROR] ggml_extend.hpp:2738 - fake_vae alloc params backend buffer failed, num_tensors = 0
[INFO ] model.cpp:795 - NOT using mmap for '/content/hidream_o1_image_dev_fp8_scaled.safetensors' (mmap disabled by caller)
[INFO ] model.cpp:807 - model files processing completed in 0.00s
|> | 1/1108 - 0.00MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.final_layer2.linear.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 4/1108 - 0.03MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.embed_tokens.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 7/1108 - 14.92MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 9/1108 - 37.37MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 11/1108 - 44.89MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 15/1108 - 59.82MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 17/1108 - 56.95MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|> | 20/1108 - 58.48MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.0.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 25/1108 - 48.85MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 27/1108 - 46.71MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 29/1108 - 45.42MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 35/1108 - 48.95MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 38/1108 - 48.45MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.1.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=> | 43/1108 - 46.16MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 45/1108 - 47.38MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 47/1108 - 48.39MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 53/1108 - 52.61MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 56/1108 - 53.15MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 58/1108 - 53.66MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.10.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 61/1108 - 50.19MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 63/1108 - 53.51MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==> | 65/1108 - 101.81MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 71/1108 - 104.44MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 74/1108 - 104.04MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.11.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 81/1108 - 102.87MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===> | 83/1108 - 104.94MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 89/1108 - 107.23MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 92/1108 - 106.83MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 94/1108 - 106.44MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.12.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 99/1108 - 104.16MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 105/1108 - 109.23MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 107/1108 - 108.03MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====> | 110/1108 - 107.66MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 112/1108 - 107.30MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.13.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 117/1108 - 105.20MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 123/1108 - 109.76MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 125/1108 - 108.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 128/1108 - 108.33MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====> | 130/1108 - 108.00MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.14.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 135/1108 - 104.86MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 137/1108 - 106.34MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 143/1108 - 105.71MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 146/1108 - 105.43MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.15.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 151/1108 - 107.04MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======> | 153/1108 - 101.52MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======> | 159/1108 - 105.19MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======> | 161/1108 - 103.38MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======> | 164/1108 - 103.16MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.16.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======> | 171/1108 - 101.57MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 179/1108 - 104.18MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 182/1108 - 103.97MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.17.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 189/1108 - 102.45MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========> | 197/1108 - 104.88MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 200/1108 - 104.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.18.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 205/1108 - 104.64MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 207/1108 - 103.23MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 215/1108 - 105.49MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========> | 218/1108 - 105.29MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.19.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 225/1108 - 103.91MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 233/1108 - 106.03MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 236/1108 - 105.84MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.2.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 241/1108 - 105.80MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========> | 243/1108 - 105.25MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 245/1108 - 106.19MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 251/1108 - 106.50MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 254/1108 - 106.32MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.20.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========> | 261/1108 - 105.05MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 269/1108 - 106.94MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 272/1108 - 106.76MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.21.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 277/1108 - 106.72MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 279/1108 - 104.22MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 285/1108 - 106.54MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============> | 287/1108 - 105.36MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 290/1108 - 104.56MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.22.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 295/1108 - 105.84MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 297/1108 - 102.88MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 299/1108 - 103.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 305/1108 - 103.97MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============> | 308/1108 - 103.83MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.23.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 315/1108 - 103.41MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 317/1108 - 104.16MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 323/1108 - 105.01MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============> | 326/1108 - 104.30MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.24.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 333/1108 - 103.88MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 335/1108 - 104.60MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 341/1108 - 104.86MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 344/1108 - 104.73MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.25.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 351/1108 - 104.33MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============> | 353/1108 - 105.01MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================> | 359/1108 - 105.26MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================> | 362/1108 - 105.13MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.26.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================> | 369/1108 - 104.22MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================> | 375/1108 - 106.04MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 377/1108 - 105.63MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 380/1108 - 105.51MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 382/1108 - 105.38MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.27.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 387/1108 - 104.62MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 393/1108 - 106.37MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 395/1108 - 105.97MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=================> | 398/1108 - 105.36MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.28.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 405/1108 - 104.52MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 413/1108 - 105.81MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 416/1108 - 105.23MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================> | 418/1108 - 105.12MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.29.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 423/1108 - 103.52MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 429/1108 - 105.12MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 431/1108 - 104.32MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 434/1108 - 103.77MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 436/1108 - 103.67MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.3.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================> | 441/1108 - 102.60MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 449/1108 - 103.79MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 452/1108 - 103.70MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 454/1108 - 103.60MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.30.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 459/1108 - 102.99MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================> | 465/1108 - 104.47MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 467/1108 - 104.14MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 470/1108 - 103.64MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.31.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 477/1108 - 103.35MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 479/1108 - 103.87MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=====================> | 485/1108 - 104.06MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 488/1108 - 103.97MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.32.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 495/1108 - 103.30MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 501/1108 - 104.69MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 503/1108 - 104.38MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 506/1108 - 104.29MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================> | 508/1108 - 104.20MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.33.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 513/1108 - 103.63MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 515/1108 - 104.12MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 521/1108 - 104.68MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 524/1108 - 104.22MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.34.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================> | 531/1108 - 103.58MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 539/1108 - 104.59MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 542/1108 - 104.51MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.35.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 549/1108 - 103.89MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================> | 551/1108 - 104.34MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 557/1108 - 104.16MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 560/1108 - 103.73MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.4.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 567/1108 - 102.47MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================> | 575/1108 - 103.08MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 578/1108 - 103.01MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.5.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 583/1108 - 103.00MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 585/1108 - 102.46MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 587/1108 - 102.89MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 593/1108 - 103.38MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==========================> | 596/1108 - 102.98MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.6.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 603/1108 - 102.76MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 605/1108 - 103.18MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 611/1108 - 103.66MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 614/1108 - 103.27MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.7.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================> | 619/1108 - 103.26MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 621/1108 - 103.04MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 623/1108 - 103.45MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 629/1108 - 103.61MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 632/1108 - 103.54MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.8.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.mlp.down_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 639/1108 - 103.31MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.mlp.gate_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================> | 641/1108 - 103.71MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.mlp.up_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.k_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============================> | 647/1108 - 103.86MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.o_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============================> | 650/1108 - 103.80MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.q_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.language_model.layers.9.self_attn.v_proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.t_embedder1.mlp.0.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.t_embedder1.mlp.2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============================> | 662/1108 - 104.49MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============================> | 671/1108 - 104.33MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.0.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.1.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===============================> | 700/1108 - 104.55MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.10.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.11.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================================> | 729/1108 - 104.60MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.12.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.13.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================================> | 758/1108 - 104.70MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.14.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===================================> | 783/1108 - 104.75MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.15.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.16.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|====================================> | 812/1108 - 104.81MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.17.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.18.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|======================================> | 844/1108 - 104.92MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.19.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.2.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=======================================> | 876/1108 - 105.04MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.20.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|========================================> | 895/1108 - 105.00MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.21.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.22.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=========================================> | 927/1108 - 105.11MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.23.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.24.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|===========================================> | 956/1108 - 105.17MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.25.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.26.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|============================================> | 985/1108 - 105.22MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.3.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.4.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|=============================================> | 1014/1108 - 105.31MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.5.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==============================================> | 1038/1108 - 105.35MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.6.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.7.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================================================> | 1068/1108 - 105.41MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.8.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.attn.proj.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.attn.qkv.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|================================================> | 1084/1108 - 105.32MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.mlp.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.blocks.9.mlp.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.visual.merger.linear_fc1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================================================| 1097/1108 - 104.64MB/s[INFO ] model.cpp:1167 - unknown tensor 'model.visual.merger.linear_fc2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.x_embedder.proj1.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
[INFO ] model.cpp:1167 - unknown tensor 'model.x_embedder.proj2.weight_scale | f32 | 1 [1, 1, 1, 1, 1]' in model file
|==================================================| 1108/1108 - 104.99MB/s
[INFO ] model.cpp:1135 - loading tensors completed, taking 73.28s (read: 23.26s, memcpy: 0.00s, convert: 46.64s, copy_to_backend: 2.13s)
[INFO ] stable-diffusion.cpp:945 - total params memory size = 15383.85MB (VRAM 14508.23MB, RAM 875.61MB): text_encoders 875.61MB(RAM), diffusion_model 14508.23MB(VRAM), vae 0.00MB(RAM), controlnet 0.00MB(VRAM), pmid 0.00MB(RAM)
[INFO ] stable-diffusion.cpp:1030 - running in FLOW mode
[INFO ] stable-diffusion.cpp:3503 - generate_image 512x512
[INFO ] denoiser.hpp:500 - get_sigmas with discrete scheduler
[INFO ] stable-diffusion.cpp:2947 - sampling using Euler method
[INFO ] stable-diffusion.cpp:3304 - get_learned_condition completed, taking 0.00s
[INFO ] stable-diffusion.cpp:3537 - generating image: 1/1 - seed 42
|==================================================| 20/20 - 1.65it/s
[INFO ] stable-diffusion.cpp:3569 - sampling completed, taking 12.74s
[INFO ] stable-diffusion.cpp:3587 - generating 1 latent images completed, taking 12.75s
[INFO ] stable-diffusion.cpp:3328 - decoding 1 latents
[INFO ] stable-diffusion.cpp:3344 - latent 1 decoded, taking 0.00s
[INFO ] stable-diffusion.cpp:3348 - decode_first_stage completed, taking 0.00s
[INFO ] stable-diffusion.cpp:3729 - generate_image completed in 12.86s
[INFO ] main.cpp:441 - save result image 0 to 'output.png' (success)
[INFO ] main.cpp:490 - 1/1 images saved

The image is blank.

[kmnnmk212-source]

!./build/bin/sd-cli -m /content/hidream_o1_image_bf16.safetensors -p "a lovely cat holding a sign says" --cfg-scale 1.0 -v -H 1024 -W 1024 --vae-on-cpu --clip-on-cpu --max-vram 13 --mmap
[DEBUG] main.cpp:550 - version: stable-diffusion.cpp version master-602-0665a7f, commit 0665a7f
[DEBUG] main.cpp:551 - System Info:
SSE3 = 1 | AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | VSX = 0 |
[DEBUG] main.cpp:552 - SDCliParams {
mode: img_gen,
output_path: "output.png",
image_path: "",
metadata_format: "text",
verbose: true,
color: false,
canny_preprocess: false,
convert_name: false,
preview_method: none,
preview_interval: 1,
preview_path: "preview.png",
preview_fps: 16,
taesd_preview: false,
preview_noisy: false,
metadata_raw: false,
metadata_brief: false,
metadata_all: false
}
[DEBUG] main.cpp:553 - SDContextParams {
n_threads: 2,
model_path: "/content/hidream_o1_image_bf16.safetensors",
clip_l_path: "",
clip_g_path: "",
clip_vision_path: "",
t5xxl_path: "",
llm_path: "",
llm_vision_path: "",
diffusion_model_path: "",
high_noise_diffusion_model_path: "",
vae_path: "",
taesd_path: "",
esrgan_path: "",
control_net_path: "",
embedding_dir: "",
embeddings: {
}
wtype: NONE,
tensor_type_rules: "",
lora_model_dir: ".",
hires_upscalers_dir: "",
photo_maker_path: "",
rng_type: cuda,
sampler_rng_type: NONE,
offload_params_to_cpu: false,
max_vram: 13,
enable_mmap: true,
control_net_cpu: false,
clip_on_cpu: true,
vae_on_cpu: true,
flash_attn: false,
diffusion_flash_attn: false,
diffusion_conv_direct: false,
vae_conv_direct: false,
circular: false,
circular_x: false,
circular_y: false,
chroma_use_dit_mask: true,
qwen_image_zero_cond_t: false,
chroma_use_t5_mask: false,
chroma_t5_mask_pad: 1,
prediction: NONE,
lora_apply_mode: auto,
force_sdxl_vae_conv_scale: false
}
[DEBUG] main.cpp:554 - SDGenerationParams {
loras: "{
}",
high_noise_loras: "{
}",
prompt: "a lovely cat holding a sign says",
negative_prompt: "",
clip_skip: -1,
width: 1024,
height: 1024,
batch_count: 1,
init_image_path: "",
end_image_path: "",
mask_image_path: "",
control_image_path: "",
ref_image_paths: [],
control_video_path: "",
auto_resize_ref_image: true,
increase_ref_index: false,
pm_id_images_dir: "",
pm_id_embed_path: "",
pm_style_strength: 20,
skip_layers: [7, 8, 9],
sample_params: (txt_cfg: 1.00, img_cfg: 1.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 20, eta: inf, shifted_timestep: 0, flow_shift: inf, extra_sample_args: ),
high_noise_skip_layers: [7, 8, 9],
high_noise_sample_params: (txt_cfg: 7.00, img_cfg: 7.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 20, eta: inf, shifted_timestep: 0, flow_shift: inf, extra_sample_args: ),
custom_sigmas: [],
cache_mode: "",
cache_option: "",
cache: disabled (threshold=inf, start=0.15, end=0.95),
moe_boundary: 0.875,
video_frames: 1,
fps: 16,
vace_strength: 1,
strength: 0.75,
control_strength: 0.9,
seed: 42,
upscale_repeats: 1,
upscale_tile_size: 128,
hires: { enabled: false, upscaler: "Latent", model_path: "", scale: 2, target_width: 0, target_height: 0, steps: 0, denoising_strength: 0.7, upscale_tile_size: 128 },
vae_tiling_params: { 0, 0, 0, 0.5, 0, 0 },
}
[INFO ] ggml_extend.hpp:63 - ggml_cuda_init: found 1 CUDA devices (Total VRAM: 14912 MiB):
[INFO ] ggml_extend.hpp:63 - Device 0: Tesla T4, compute capability 7.5, VMM: yes, VRAM: 14912 MiB
[DEBUG] util.cpp:781 - Found 2 backend devices:
[DEBUG] util.cpp:784 - #0: CUDA0
[DEBUG] util.cpp:784 - #1: CPU
[DEBUG] ggml_extend.hpp:110 - Initializing backend: CUDA0
[INFO ] stable-diffusion.cpp:216 - loading model from '/content/hidream_o1_image_bf16.safetensors'
[INFO ] model.cpp:219 - load /content/hidream_o1_image_bf16.safetensors using safetensors format
[DEBUG] model.cpp:294 - init from '/content/hidream_o1_image_bf16.safetensors', prefix = ''
[INFO ] stable-diffusion.cpp:309 - Version: HiDream O1
[INFO ] stable-diffusion.cpp:337 - Weight type stat: bf16: 758
[INFO ] stable-diffusion.cpp:338 - Conditioner weight type stat:
[INFO ] stable-diffusion.cpp:339 - Diffusion model weight type stat:
[INFO ] stable-diffusion.cpp:340 - VAE weight type stat:
[DEBUG] stable-diffusion.cpp:342 - ggml tensor size = 400 bytes
[WARN ] stable-diffusion.cpp:374 - in mode 'immediately', LoRAs will cause extra memory usage with mmap
[INFO ] stable-diffusion.cpp:436 - CLIP: Using CPU backend
[DEBUG] qwen2_tokenizer.cpp:14 - merges size 151387
[DEBUG] qwen2_tokenizer.cpp:39 - vocab size: 151674
[INFO ] stable-diffusion.cpp:622 - VAE Autoencoder: Using CPU backend
[INFO ] stable-diffusion.cpp:684 - using FakeVAE
[DEBUG] stable-diffusion.cpp:814 - loading weights
[DEBUG] model.cpp:779 - using mmap for I/O
[INFO ] model.cpp:785 - using mmap for '/content/hidream_o1_image_bf16.safetensors'
[INFO ] model.cpp:807 - model files processing completed in 0.00s
[DEBUG] model.cpp:819 - memory-mapping tensors...
[INFO ] model.cpp:887 - memory-mapped 110 tensors in 1 files (860.55 MB), taking 0.00s
[DEBUG] ggml_extend.hpp:2746 - hidream_o1_vision params backend buffer size = 15.06 MB(RAM) (333 tensors)
[ERROR] ggml_extend.hpp:69 - ggml_backend_cuda_buffer_type_alloc_buffer: allocating 15695.23 MiB on device 0: cudaMalloc failed: out of memory
[ERROR] ggml_extend.hpp:69 - alloc_tensor_range: failed to allocate CUDA0 buffer of size 16457646080
[ERROR] ggml_extend.hpp:2738 - hidream_o1 alloc params backend buffer failed, num_tensors = 407
[ERROR] ggml_extend.hpp:2738 - fake_vae alloc params backend buffer failed, num_tensors = 0
[DEBUG] model.cpp:906 - using 2 threads for model loading
[DEBUG] model.cpp:922 - loading tensors from /content/hidream_o1_image_bf16.safetensors
[ERROR] model.cpp:1071 - read tensor data failed: too less memory for conversion
[INFO ] model.cpp:1135 - loading tensors completed, taking 0.00s (read: 0.00s, memcpy: 0.00s, convert: 0.00s, copy_to_backend: 0.00s)
[ERROR] model.cpp:1192 - load tensors from file failed
[ERROR] stable-diffusion.cpp:888 - load tensors from model loader failed
[INFO ] main.cpp:713 - new_sd_ctx_t failed

[kmnnmk212-source]

!./build/bin/sd-cli -m /content/hidream_o1_image_bf16.safetensors -p "a lovely cat holding a sign says" --cfg-scale 1.0 -v -H 64 -W 64 --vae-on-cpu --clip-on-cpu --max-vram 13 --mmap --type q2_K --sampler-rng cpu

[DEBUG] main.cpp:550 - version: stable-diffusion.cpp version master-602-0665a7f, commit 0665a7f
[DEBUG] main.cpp:551 - System Info:
SSE3 = 1 | AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | VSX = 0 |
[DEBUG] main.cpp:552 - SDCliParams {
mode: img_gen,
output_path: "output.png",
image_path: "",
metadata_format: "text",
verbose: true,
color: false,
canny_preprocess: false,
convert_name: false,
preview_method: none,
preview_interval: 1,
preview_path: "preview.png",
preview_fps: 16,
taesd_preview: false,
preview_noisy: false,
metadata_raw: false,
metadata_brief: false,
metadata_all: false
}
[DEBUG] main.cpp:553 - SDContextParams {
n_threads: 2,
model_path: "/content/hidream_o1_image_bf16.safetensors",
clip_l_path: "",
clip_g_path: "",
clip_vision_path: "",
t5xxl_path: "",
llm_path: "",
llm_vision_path: "",
diffusion_model_path: "",
high_noise_diffusion_model_path: "",
vae_path: "",
taesd_path: "",
esrgan_path: "",
control_net_path: "",
embedding_dir: "",
embeddings: {
}
wtype: q2_K,
tensor_type_rules: "",
lora_model_dir: ".",
hires_upscalers_dir: "",
photo_maker_path: "",
rng_type: cuda,
sampler_rng_type: cpu,
offload_params_to_cpu: false,
max_vram: 13,
enable_mmap: true,
control_net_cpu: false,
clip_on_cpu: true,
vae_on_cpu: true,
flash_attn: false,
diffusion_flash_attn: false,
diffusion_conv_direct: false,
vae_conv_direct: false,
circular: false,
circular_x: false,
circular_y: false,
chroma_use_dit_mask: true,
qwen_image_zero_cond_t: false,
chroma_use_t5_mask: false,
chroma_t5_mask_pad: 1,
prediction: NONE,
lora_apply_mode: auto,
force_sdxl_vae_conv_scale: false
}
[DEBUG] main.cpp:554 - SDGenerationParams {
loras: "{
}",
high_noise_loras: "{
}",
prompt: "a lovely cat holding a sign says",
negative_prompt: "",
clip_skip: -1,
width: 64,
height: 64,
batch_count: 1,
init_image_path: "",
end_image_path: "",
mask_image_path: "",
control_image_path: "",
ref_image_paths: [],
control_video_path: "",
auto_resize_ref_image: true,
increase_ref_index: false,
pm_id_images_dir: "",
pm_id_embed_path: "",
pm_style_strength: 20,
skip_layers: [7, 8, 9],
sample_params: (txt_cfg: 1.00, img_cfg: 1.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 20, eta: inf, shifted_timestep: 0, flow_shift: inf, extra_sample_args: ),
high_noise_skip_layers: [7, 8, 9],
high_noise_sample_params: (txt_cfg: 7.00, img_cfg: 7.00, distilled_guidance: 3.50, slg.layer_count: 0, slg.layer_start: 0.01, slg.layer_end: 0.20, slg.scale: 0.00, scheduler: NONE, sample_method: NONE, sample_steps: 20, eta: inf, shifted_timestep: 0, flow_shift: inf, extra_sample_args: ),
custom_sigmas: [],
cache_mode: "",
cache_option: "",
cache: disabled (threshold=inf, start=0.15, end=0.95),
moe_boundary: 0.875,
video_frames: 1,
fps: 16,
vace_strength: 1,
strength: 0.75,
control_strength: 0.9,
seed: 42,
upscale_repeats: 1,
upscale_tile_size: 128,
hires: { enabled: false, upscaler: "Latent", model_path: "", scale: 2, target_width: 0, target_height: 0, steps: 0, denoising_strength: 0.7, upscale_tile_size: 128 },
vae_tiling_params: { 0, 0, 0, 0.5, 0, 0 },
}
[INFO ] ggml_extend.hpp:63 - ggml_cuda_init: found 1 CUDA devices (Total VRAM: 14912 MiB):
[INFO ] ggml_extend.hpp:63 - Device 0: Tesla T4, compute capability 7.5, VMM: yes, VRAM: 14912 MiB
[DEBUG] util.cpp:781 - Found 2 backend devices:
[DEBUG] util.cpp:784 - #0: CUDA0
[DEBUG] util.cpp:784 - #1: CPU
[DEBUG] ggml_extend.hpp:110 - Initializing backend: CUDA0
[INFO ] stable-diffusion.cpp:216 - loading model from '/content/hidream_o1_image_bf16.safetensors'
[INFO ] model.cpp:219 - load /content/hidream_o1_image_bf16.safetensors using safetensors format
[DEBUG] model.cpp:294 - init from '/content/hidream_o1_image_bf16.safetensors', prefix = ''
[INFO ] stable-diffusion.cpp:309 - Version: HiDream O1
[INFO ] stable-diffusion.cpp:337 - Weight type stat: bf16: 758
[INFO ] stable-diffusion.cpp:338 - Conditioner weight type stat:
[INFO ] stable-diffusion.cpp:339 - Diffusion model weight type stat:
[INFO ] stable-diffusion.cpp:340 - VAE weight type stat:
[DEBUG] stable-diffusion.cpp:342 - ggml tensor size = 400 bytes
[INFO ] stable-diffusion.cpp:436 - CLIP: Using CPU backend
[DEBUG] qwen2_tokenizer.cpp:14 - merges size 151387
[DEBUG] qwen2_tokenizer.cpp:39 - vocab size: 151674
[INFO ] stable-diffusion.cpp:622 - VAE Autoencoder: Using CPU backend
[INFO ] stable-diffusion.cpp:684 - using FakeVAE
[DEBUG] stable-diffusion.cpp:814 - loading weights
[DEBUG] model.cpp:779 - using mmap for I/O
[INFO ] model.cpp:785 - using mmap for '/content/hidream_o1_image_bf16.safetensors'
[INFO ] model.cpp:807 - model files processing completed in 0.00s
[DEBUG] model.cpp:819 - memory-mapping tensors...
[INFO ] model.cpp:887 - memory-mapped 108 tensors in 1 files (784.05 MB), taking 0.00s
[DEBUG] ggml_extend.hpp:2746 - hidream_o1_vision params backend buffer size = 27.61 MB(RAM) (333 tensors)
[DEBUG] ggml_extend.hpp:2746 - hidream_o1 params backend buffer size = 4572.25 MB(VRAM) (407 tensors)
[ERROR] ggml_extend.hpp:2738 - fake_vae alloc params backend buffer failed, num_tensors = 0
[DEBUG] model.cpp:906 - using 2 threads for model loading
[DEBUG] model.cpp:922 - loading tensors from /content/hidream_o1_image_bf16.safetensors
|=> | 28/758 - 19.24MB/s

[wbruna]

I believe scaled fp8 models are not supported.

--max-vram should work, but you need to enable offloading too (--offload-to-cpu).

Anyway, for 16G VRAM, you may try quantizing it in the way I've described in #1496 :

sd-cli -M convert -m hidream_o1_image_bf16.safetensors --tensor-type-rules "^model\.language_model\.layers\.[0-9]+\.mlp\.(gate|up)_proj\.weight=q8_0" -o hidream_o1_image-Q8_0.gguf

or (smaller, possibly less quality):

sd-cli -M convert -m hidream_o1_image_bf16.safetensors --tensor-type-rules "^model\.language_model\.layers\.[0-9]+\.mlp\.(gate|up)_proj\.weight=q8_0,^model\.language_model\.layers\.[0-9]+\.self_attn\.[kqvo]_proj\.weight=q8_0" -o hidream_o1_image-Q8_0.gguf

[kmnnmk212-source]

thank you wbruna

/content/hidream_o1_image_fp8_scaled.safetensors
/content/hidream_o1_image_dev_fp8_scaled.safetensors
blaack image

ask can it
sd-cli -M convert -m hidream_o1_image_bf16.safetensors --tensor-type-rules "^model.language_model.layers.[0-9]+.mlp.(gate|up)_proj.weight=q8_0" -o hidream_o1_image-Q8_0.gguf
run on cloabb t4?

[kmnnmk212-source]

!./build/bin/sd-cli -M convert -m /content/hidream_o1_image_bf16.safetensors --tensor-type-rules "^model.language_model.layers.[0-9]+.mlp.(gate|up)_proj.weight=q8_0,^model.language_model.layers.[0-9]+.self_attn.[kqvo]_proj.weight=q8_0" -o hidream_o1_image-Q8_0.gguf --rng

[ERROR] common.cpp:286 - error: invalid parameter for argument: --rng
stable-diffusion.cpp version master-602-0665a7f, commit 0665a7f
Usage: ./build/bin/sd-cli [options]

CLI Options:
-o, --output path to write result image to. you can use printf-style %d format specifiers for image
sequences (default: ./output.png) (eg. output_%03d.png). Single-file video outputs
support .avi, .webm, and animated .webp
--image path to the image to inspect (for metadata mode)
--metadata-format metadata output format, one of [text, json] (default: text)
--preview-path path to write preview image to (default: ./preview.png). Multi-frame previews support
.avi, .webm, and animated .webp
--preview-interval interval in denoising steps between consecutive updates of the image preview file
(default is 1, meaning updating at every step)
--output-begin-idx starting index for output image sequence, must be non-negative (default 0 if specified
%d in output path, 1 otherwise)
--canny apply canny preprocessor (edge detection)
--convert-name convert tensor name (for convert mode)
-v, --verbose print extra info
--color colors the logging tags according to level
--taesd-preview-only prevents usage of taesd for decoding the final image. (for use with --preview tae)
--preview-noisy enables previewing noisy inputs of the models rather than the denoised outputs
--metadata-raw include raw hex previews for unparsed metadata payloads
--metadata-brief truncate long metadata text values in text output
--metadata-all include structural/container entries such as IHDR, IDAT, and non-metadata JPEG segments
-M, --mode run mode, one of [img_gen, vid_gen, upscale, convert, metadata], default: img_gen
--preview preview method. must be one of the following [none, proj, tae, vae] (default is none)
-h, --help show this help message and exit

Context Options:
-m, --model path to full model
--clip_l path to the clip-l text encoder
--clip_g path to the clip-g text encoder
--clip_vision path to the clip-vision encoder
--t5xxl path to the t5xxl text encoder
--llm path to the llm text encoder. For example: (qwenvl2.5 for qwen-image,
mistral-small3.2 for flux2, ...)
--llm_vision path to the llm vit
--qwen2vl alias of --llm. Deprecated.
--qwen2vl_vision alias of --llm_vision. Deprecated.
--diffusion-model path to the standalone diffusion model
--high-noise-diffusion-model path to the standalone high noise diffusion model
--vae path to standalone vae model
--taesd path to taesd. Using Tiny AutoEncoder for fast decoding (low quality)
--tae alias of --taesd
--control-net path to control net model
--embd-dir embeddings directory
--lora-model-dir lora model directory
--hires-upscalers-dir highres fix upscaler model directory
--tensor-type-rules weight type per tensor pattern (example: "^vae.=f16,model.=q8_0")
--photo-maker path to PHOTOMAKER model
--upscale-model path to esrgan model.
-t, --threads number of threads to use during computation (default: -1). If threads <= 0,
then threads will be set to the number of CPU physical cores
--chroma-t5-mask-pad t5 mask pad size of chroma
--max-vram maximum VRAM budget in GiB for graph-cut segmented execution. 0 disables
graph splitting
--force-sdxl-vae-conv-scale force use of conv scale on sdxl vae
--offload-to-cpu place the weights in RAM to save VRAM, and automatically load them into VRAM
when needed
--mmap whether to memory-map model
--control-net-cpu keep controlnet in cpu (for low vram)
--clip-on-cpu keep clip in cpu (for low vram)
--vae-on-cpu keep vae in cpu (for low vram)
--fa use flash attention
--diffusion-fa use flash attention in the diffusion model only
--diffusion-conv-direct use ggml_conv2d_direct in the diffusion model
--vae-conv-direct use ggml_conv2d_direct in the vae model
--circular enable circular padding for convolutions
--circularx enable circular RoPE wrapping on x-axis (width) only
--circulary enable circular RoPE wrapping on y-axis (height) only
--chroma-disable-dit-mask disable dit mask for chroma
--qwen-image-zero-cond-t enable zero_cond_t for qwen image
--chroma-enable-t5-mask enable t5 mask for chroma
--type weight type (examples: f32, f16, q4_0, q4_1, q5_0, q5_1, q8_0, q2_K, q3_K,
q4_K). If not specified, the default is the type of the weight file
--rng RNG, one of [std_default, cuda, cpu], default: cuda(sd-webui), cpu(comfyui)
--sampler-rng sampler RNG, one of [std_default, cuda, cpu]. If not specified, use --rng
--prediction prediction type override, one of [eps, v, edm_v, sd3_flow, flux_flow,
flux2_flow]
--lora-apply-mode the way to apply LoRA, one of [auto, immediately, at_runtime], default is
auto. In auto mode, if the model weights contain any quantized parameters,
the at_runtime mode will be used; otherwise, immediately will be used.The
immediately mode may have precision and compatibility issues with quantized
parameters, but it usually offers faster inference speed and, in some cases,
lower memory usage. The at_runtime mode, on the other hand, is exactly the
opposite.

Generation Options:
-p, --prompt the prompt to render
-n, --negative-prompt the negative prompt (default: "")
-i, --init-img path to the init image
--end-img path to the end image, required by flf2v
--mask path to the mask image
--control-image path to control image, control net
--control-video path to control video frames, It must be a directory path. The video frames
inside should be stored as images in lexicographical (character) order. For
example, if the control video path is frames, the directory contain images
such as 00.png, 01.png, ... etc.
--pm-id-images-dir path to PHOTOMAKER input id images dir
--pm-id-embed-path path to PHOTOMAKER v2 id embed
--hires-upscaler highres fix upscaler, Lanczos, Nearest, Latent, Latent (nearest), Latent
(nearest-exact), Latent (antialiased), Latent (bicubic), Latent (bicubic
antialiased), or a model name under --hires-upscalers-dir (default: Latent)
--extra-sample-args extra sampler args, key=value list. Currently lcm supports noise_clip_std,
noise_scale_start, noise_scale_end
-H, --height image height, in pixel space (default: 512)
-W, --width image width, in pixel space (default: 512)
--steps number of sample steps (default: 20)
--high-noise-steps (high noise) number of sample steps (default: -1 = auto)
--clip-skip ignore last layers of CLIP network; 1 ignores none, 2 ignores one layer
(default: -1). <= 0 represents unspecified, will be 1 for SD1.x, 2 for SD2.x
-b, --batch-count batch count
--video-frames video frames (default: 1)
--fps fps (default: 24)
--timestep-shift shift timestep for NitroFusion models (default: 0). recommended N for
NitroSD-Realism around 250 and 500 for NitroSD-Vibrant
--upscale-repeats Run the ESRGAN upscaler this many times (default: 1)
--upscale-tile-size tile size for ESRGAN upscaling (default: 128)
--hires-width highres fix target width, 0 to use --hires-scale (default: 0)
--hires-height highres fix target height, 0 to use --hires-scale (default: 0)
--hires-steps highres fix second pass sample steps, 0 to reuse --steps (default: 0)
--hires-upscale-tile-size highres fix upscaler tile size, reserved for model-backed upscalers (default:
128)
--cfg-scale unconditional guidance scale: (default: 7.0)
--img-cfg-scale image guidance scale for inpaint or instruct-pix2pix models: (default: same
as --cfg-scale)
--guidance distilled guidance scale for models with guidance input (default: 3.5)
--slg-scale skip layer guidance (SLG) scale, only for DiT models: (default: 0). 0 means
disabled, a value of 2.5 is nice for sd3.5 medium
--skip-layer-start SLG enabling point (default: 0.01)
--skip-layer-end SLG disabling point (default: 0.2)
--eta noise multiplier (default: 0 for ddim_trailing, tcd, res_multistep and
res_2s; 1 for euler_a, er_sde and dpm++2s_a)
--flow-shift shift value for Flow models like SD3.x or WAN (default: auto)
--high-noise-cfg-scale (high noise) unconditional guidance scale: (default: 7.0)
--high-noise-img-cfg-scale (high noise) image guidance scale for inpaint or instruct-pix2pix models
(default: same as --cfg-scale)
--high-noise-guidance (high noise) distilled guidance scale for models with guidance input
(default: 3.5)
--high-noise-slg-scale (high noise) skip layer guidance (SLG) scale, only for DiT models: (default:
0)
--high-noise-skip-layer-start (high noise) SLG enabling point (default: 0.01)
--high-noise-skip-layer-end (high noise) SLG disabling point (default: 0.2)
--high-noise-eta (high noise) noise multiplier (default: 0 for ddim_trailing, tcd,
res_multistep and res_2s; 1 for euler_a, er_sde and dpm++2s_a)
--strength strength for noising/unnoising (default: 0.75)
--pm-style-strength
--control-strength strength to apply Control Net (default: 0.9). 1.0 corresponds to full
destruction of information in init image
--moe-boundary timestep boundary for Wan2.2 MoE model. (default: 0.875). Only enabled if
--high-noise-steps is set to -1
--vace-strength wan vace strength
--vae-tile-overlap tile overlap for vae tiling, in fraction of tile size (default: 0.5)
--hires-scale highres fix scale when target size is not set (default: 2.0)
--hires-denoising-strength highres fix second pass denoising strength (default: 0.7)
--increase-ref-index automatically increase the indices of references images based on the order
they are listed (starting with 1).
--disable-auto-resize-ref-image disable auto resize of ref images
--disable-image-metadata do not embed generation metadata on image files
--vae-tiling process vae in tiles to reduce memory usage
--hires enable highres fix
-s, --seed RNG seed (default: 42, use random seed for < 0)
--sampling-method sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m,
dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd, res_multistep, res_2s,
er_sde, euler_cfg_pp, euler_a_cfg_pp](default: euler for Flux/SD3/Wan,
euler_a otherwise)
--high-noise-sampling-method (high noise) sampling method, one of [euler, euler_a, heun, dpm2, dpm++2s_a,
dpm++2m, dpm++2mv2, ipndm, ipndm_v, lcm, ddim_trailing, tcd, res_multistep,
res_2s, er_sde, euler_cfg_pp, euler_a_cfg_pp] default: euler for
Flux/SD3/Wan, euler_a otherwise
--scheduler denoiser sigma scheduler, one of [discrete, karras, exponential, ays, gits,
smoothstep, sgm_uniform, simple, kl_optimal, lcm, bong_tangent], default:
discrete
--sigmas custom sigma values for the sampler, comma-separated (e.g.,
"14.61,7.8,3.5,0.0").
--skip-layers layers to skip for SLG steps (default: [7,8,9])
--high-noise-skip-layers (high noise) layers to skip for SLG steps (default: [7,8,9])
-r, --ref-image reference image for Flux Kontext models (can be used multiple times)
--cache-mode caching method: 'easycache' (DiT), 'ucache' (UNET),
'dbcache'/'taylorseer'/'cache-dit' (DiT block-level), 'spectrum' (UNET/DiT
Chebyshev+Taylor forecasting)
--cache-option named cache params (key=value format, comma-separated). easycache/ucache:
threshold=,start=,end=,decay=,relative=,reset=; dbcache/taylorseer/cache-dit:
Fn=,Bn=,threshold=,warmup=; spectrum: w=,m=,lam=,window=,flex=,warmup=,stop=.
Examples: "threshold=0.25" or "threshold=1.5,reset=0"
--scm-mask SCM steps mask for cache-dit: comma-separated 0/1 (e.g.,
"1,1,1,0,0,1,0,0,1,0") - 1=compute, 0=can cache
--scm-policy SCM policy: 'dynamic' (default) or 'static'
--vae-tile-size tile size for vae tiling, format [X]x[Y] (default: 32x32)
--vae-relative-tile-size relative tile size for vae tiling, format [X]x[Y], in fraction of image size
if < 1, in number of tiles per dim if >=1 (overrides --vae-tile-size)

[kmnnmk212-source]

!./build/bin/sd-cli -M convert -m /content/hidream_o1_image_bf16.safetensors --tensor-type-rules "^model.language_model.layers.[0-9]+.mlp.(gate|up)_proj.weight=q8_0,^model.language_model.layers.[0-9]+.self_attn.[kqvo]_proj.weight=q8_0" -o hidream_o1_image-Q8_0.gguf --rng
crash ram on colab t4