Image-Text-to-Text
Transformers
Safetensors
minimax_m3_vl
multimodal
Mixture of Experts
agent
coding
video
conversational
custom_code
8-bit precision
quark
Instructions to use amd/MiniMax-M3-MXFP4-AttnFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amd/MiniMax-M3-MXFP4-AttnFP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="amd/MiniMax-M3-MXFP4-AttnFP8", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("amd/MiniMax-M3-MXFP4-AttnFP8", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("amd/MiniMax-M3-MXFP4-AttnFP8", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use amd/MiniMax-M3-MXFP4-AttnFP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "amd/MiniMax-M3-MXFP4-AttnFP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amd/MiniMax-M3-MXFP4-AttnFP8", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/amd/MiniMax-M3-MXFP4-AttnFP8
- SGLang
How to use amd/MiniMax-M3-MXFP4-AttnFP8 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "amd/MiniMax-M3-MXFP4-AttnFP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amd/MiniMax-M3-MXFP4-AttnFP8", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "amd/MiniMax-M3-MXFP4-AttnFP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amd/MiniMax-M3-MXFP4-AttnFP8", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use amd/MiniMax-M3-MXFP4-AttnFP8 with Docker Model Runner:
docker model run hf.co/amd/MiniMax-M3-MXFP4-AttnFP8
upload model with quantized index
#2
by jiaxwang - opened
This view is limited to 50 files because it contains too many changes. See the raw diff here.
- chat_template.jinja +5 -5
- config.json +10 -115
- figures/benchmark.jpeg +3 -0
- figures/efficiency_gqa_vs_msa.png +0 -0
- figures/logo.svg +16 -0
- generation_config.json +8 -0
- model-00001-of-00059.safetensors +2 -2
- model-00002-of-00059.safetensors +2 -2
- model-00003-of-00059.safetensors +2 -2
- model-00004-of-00059.safetensors +2 -2
- model-00005-of-00059.safetensors +2 -2
- model-00006-of-00059.safetensors +2 -2
- model-00007-of-00059.safetensors +2 -2
- model-00008-of-00059.safetensors +2 -2
- model-00009-of-00059.safetensors +2 -2
- model-00010-of-00059.safetensors +2 -2
- model-00011-of-00059.safetensors +2 -2
- model-00012-of-00059.safetensors +2 -2
- model-00013-of-00059.safetensors +2 -2
- model-00014-of-00059.safetensors +2 -2
- model-00015-of-00059.safetensors +2 -2
- model-00016-of-00059.safetensors +2 -2
- model-00017-of-00059.safetensors +2 -2
- model-00018-of-00059.safetensors +2 -2
- model-00019-of-00059.safetensors +2 -2
- model-00020-of-00059.safetensors +2 -2
- model-00021-of-00059.safetensors +2 -2
- model-00022-of-00059.safetensors +2 -2
- model-00023-of-00059.safetensors +2 -2
- model-00024-of-00059.safetensors +2 -2
- model-00025-of-00059.safetensors +2 -2
- model-00026-of-00059.safetensors +2 -2
- model-00027-of-00059.safetensors +2 -2
- model-00028-of-00059.safetensors +2 -2
- model-00029-of-00059.safetensors +2 -2
- model-00030-of-00059.safetensors +2 -2
- model-00031-of-00059.safetensors +2 -2
- model-00032-of-00059.safetensors +2 -2
- model-00033-of-00059.safetensors +2 -2
- model-00034-of-00059.safetensors +2 -2
- model-00035-of-00059.safetensors +2 -2
- model-00036-of-00059.safetensors +2 -2
- model-00037-of-00059.safetensors +2 -2
- model-00038-of-00059.safetensors +2 -2
- model-00039-of-00059.safetensors +2 -2
- model-00040-of-00059.safetensors +2 -2
- model-00041-of-00059.safetensors +2 -2
- model-00042-of-00059.safetensors +2 -2
- model-00043-of-00059.safetensors +2 -2
- model-00044-of-00059.safetensors +2 -2
chat_template.jinja
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
{%- set think_begin_token = '<mm:think>' -%}
|
| 9 |
{%- set think_end_token = '</mm:think>' -%}
|
| 10 |
{%- set image_token = ']<]image[>[' -%}
|
| 11 |
-
{%- set
|
| 12 |
{#- Thinking mode: "enabled" / "disabled" / "adaptive" / not defined -#}
|
| 13 |
{#- Recursive XML renderer for tool_call arguments ======================== -#}
|
| 14 |
{#- None values are intentionally skipped in mapping iteration so that
|
|
@@ -49,8 +49,8 @@
|
|
| 49 |
{{- item.text }}
|
| 50 |
{%- elif item is mapping and item.type == 'image' -%}
|
| 51 |
{{- image_token }}
|
| 52 |
-
{%- elif item is mapping and item.type == '
|
| 53 |
-
{{-
|
| 54 |
{%- elif item is string -%}
|
| 55 |
{{- item }}
|
| 56 |
{%- endif -%}
|
|
@@ -212,8 +212,8 @@
|
|
| 212 |
{%- for tr in message.content -%}
|
| 213 |
{%- if tr is mapping and tr.type is defined and tr.type == 'image' -%}
|
| 214 |
{{- image_token }}
|
| 215 |
-
{%- elif tr is mapping and tr.type is defined and tr.type == '
|
| 216 |
-
{{-
|
| 217 |
{%- else -%}
|
| 218 |
{{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
|
| 219 |
{%- endif -%}
|
|
|
|
| 8 |
{%- set think_begin_token = '<mm:think>' -%}
|
| 9 |
{%- set think_end_token = '</mm:think>' -%}
|
| 10 |
{%- set image_token = ']<]image[>[' -%}
|
| 11 |
+
{%- set video_token = ']<]video[>[' -%}
|
| 12 |
{#- Thinking mode: "enabled" / "disabled" / "adaptive" / not defined -#}
|
| 13 |
{#- Recursive XML renderer for tool_call arguments ======================== -#}
|
| 14 |
{#- None values are intentionally skipped in mapping iteration so that
|
|
|
|
| 49 |
{{- item.text }}
|
| 50 |
{%- elif item is mapping and item.type == 'image' -%}
|
| 51 |
{{- image_token }}
|
| 52 |
+
{%- elif item is mapping and item.type == 'video' -%}
|
| 53 |
+
{{- video_token}}
|
| 54 |
{%- elif item is string -%}
|
| 55 |
{{- item }}
|
| 56 |
{%- endif -%}
|
|
|
|
| 212 |
{%- for tr in message.content -%}
|
| 213 |
{%- if tr is mapping and tr.type is defined and tr.type == 'image' -%}
|
| 214 |
{{- image_token }}
|
| 215 |
+
{%- elif tr is mapping and tr.type is defined and tr.type == 'video' -%}
|
| 216 |
+
{{- video_token }}
|
| 217 |
{%- else -%}
|
| 218 |
{{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
|
| 219 |
{%- endif -%}
|
config.json
CHANGED
|
@@ -325,177 +325,72 @@
|
|
| 325 |
},
|
| 326 |
"exclude": [
|
| 327 |
"language_model.lm_head",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 328 |
"language_model.model.layers.10.block_sparse_moe.gate",
|
| 329 |
-
"language_model.model.layers.10.self_attn.index_k_proj",
|
| 330 |
-
"language_model.model.layers.10.self_attn.index_q_proj",
|
| 331 |
"language_model.model.layers.11.block_sparse_moe.gate",
|
| 332 |
-
"language_model.model.layers.11.self_attn.index_k_proj",
|
| 333 |
-
"language_model.model.layers.11.self_attn.index_q_proj",
|
| 334 |
"language_model.model.layers.12.block_sparse_moe.gate",
|
| 335 |
-
"language_model.model.layers.12.self_attn.index_k_proj",
|
| 336 |
-
"language_model.model.layers.12.self_attn.index_q_proj",
|
| 337 |
"language_model.model.layers.13.block_sparse_moe.gate",
|
| 338 |
-
"language_model.model.layers.13.self_attn.index_k_proj",
|
| 339 |
-
"language_model.model.layers.13.self_attn.index_q_proj",
|
| 340 |
"language_model.model.layers.14.block_sparse_moe.gate",
|
| 341 |
-
"language_model.model.layers.14.self_attn.index_k_proj",
|
| 342 |
-
"language_model.model.layers.14.self_attn.index_q_proj",
|
| 343 |
"language_model.model.layers.15.block_sparse_moe.gate",
|
| 344 |
-
"language_model.model.layers.15.self_attn.index_k_proj",
|
| 345 |
-
"language_model.model.layers.15.self_attn.index_q_proj",
|
| 346 |
"language_model.model.layers.16.block_sparse_moe.gate",
|
| 347 |
-
"language_model.model.layers.16.self_attn.index_k_proj",
|
| 348 |
-
"language_model.model.layers.16.self_attn.index_q_proj",
|
| 349 |
"language_model.model.layers.17.block_sparse_moe.gate",
|
| 350 |
-
"language_model.model.layers.17.self_attn.index_k_proj",
|
| 351 |
-
"language_model.model.layers.17.self_attn.index_q_proj",
|
| 352 |
"language_model.model.layers.18.block_sparse_moe.gate",
|
| 353 |
-
"language_model.model.layers.18.self_attn.index_k_proj",
|
| 354 |
-
"language_model.model.layers.18.self_attn.index_q_proj",
|
| 355 |
"language_model.model.layers.19.block_sparse_moe.gate",
|
| 356 |
-
"language_model.model.layers.
|
| 357 |
-
"language_model.model.layers.
|
|
|
|
| 358 |
"language_model.model.layers.20.block_sparse_moe.gate",
|
| 359 |
-
"language_model.model.layers.20.self_attn.index_k_proj",
|
| 360 |
-
"language_model.model.layers.20.self_attn.index_q_proj",
|
| 361 |
"language_model.model.layers.21.block_sparse_moe.gate",
|
| 362 |
-
"language_model.model.layers.21.self_attn.index_k_proj",
|
| 363 |
-
"language_model.model.layers.21.self_attn.index_q_proj",
|
| 364 |
"language_model.model.layers.22.block_sparse_moe.gate",
|
| 365 |
-
"language_model.model.layers.22.self_attn.index_k_proj",
|
| 366 |
-
"language_model.model.layers.22.self_attn.index_q_proj",
|
| 367 |
"language_model.model.layers.23.block_sparse_moe.gate",
|
| 368 |
-
"language_model.model.layers.23.self_attn.index_k_proj",
|
| 369 |
-
"language_model.model.layers.23.self_attn.index_q_proj",
|
| 370 |
"language_model.model.layers.24.block_sparse_moe.gate",
|
| 371 |
-
"language_model.model.layers.24.self_attn.index_k_proj",
|
| 372 |
-
"language_model.model.layers.24.self_attn.index_q_proj",
|
| 373 |
"language_model.model.layers.25.block_sparse_moe.gate",
|
| 374 |
-
"language_model.model.layers.25.self_attn.index_k_proj",
|
| 375 |
-
"language_model.model.layers.25.self_attn.index_q_proj",
|
| 376 |
"language_model.model.layers.26.block_sparse_moe.gate",
|
| 377 |
-
"language_model.model.layers.26.self_attn.index_k_proj",
|
| 378 |
-
"language_model.model.layers.26.self_attn.index_q_proj",
|
| 379 |
"language_model.model.layers.27.block_sparse_moe.gate",
|
| 380 |
-
"language_model.model.layers.27.self_attn.index_k_proj",
|
| 381 |
-
"language_model.model.layers.27.self_attn.index_q_proj",
|
| 382 |
"language_model.model.layers.28.block_sparse_moe.gate",
|
| 383 |
-
"language_model.model.layers.28.self_attn.index_k_proj",
|
| 384 |
-
"language_model.model.layers.28.self_attn.index_q_proj",
|
| 385 |
"language_model.model.layers.29.block_sparse_moe.gate",
|
| 386 |
-
"language_model.model.layers.29.self_attn.index_k_proj",
|
| 387 |
-
"language_model.model.layers.29.self_attn.index_q_proj",
|
| 388 |
"language_model.model.layers.3.block_sparse_moe.gate",
|
| 389 |
-
"language_model.model.layers.3.self_attn.index_k_proj",
|
| 390 |
-
"language_model.model.layers.3.self_attn.index_q_proj",
|
| 391 |
"language_model.model.layers.30.block_sparse_moe.gate",
|
| 392 |
-
"language_model.model.layers.30.self_attn.index_k_proj",
|
| 393 |
-
"language_model.model.layers.30.self_attn.index_q_proj",
|
| 394 |
"language_model.model.layers.31.block_sparse_moe.gate",
|
| 395 |
-
"language_model.model.layers.31.self_attn.index_k_proj",
|
| 396 |
-
"language_model.model.layers.31.self_attn.index_q_proj",
|
| 397 |
"language_model.model.layers.32.block_sparse_moe.gate",
|
| 398 |
-
"language_model.model.layers.32.self_attn.index_k_proj",
|
| 399 |
-
"language_model.model.layers.32.self_attn.index_q_proj",
|
| 400 |
"language_model.model.layers.33.block_sparse_moe.gate",
|
| 401 |
-
"language_model.model.layers.33.self_attn.index_k_proj",
|
| 402 |
-
"language_model.model.layers.33.self_attn.index_q_proj",
|
| 403 |
"language_model.model.layers.34.block_sparse_moe.gate",
|
| 404 |
-
"language_model.model.layers.34.self_attn.index_k_proj",
|
| 405 |
-
"language_model.model.layers.34.self_attn.index_q_proj",
|
| 406 |
"language_model.model.layers.35.block_sparse_moe.gate",
|
| 407 |
-
"language_model.model.layers.35.self_attn.index_k_proj",
|
| 408 |
-
"language_model.model.layers.35.self_attn.index_q_proj",
|
| 409 |
"language_model.model.layers.36.block_sparse_moe.gate",
|
| 410 |
-
"language_model.model.layers.36.self_attn.index_k_proj",
|
| 411 |
-
"language_model.model.layers.36.self_attn.index_q_proj",
|
| 412 |
"language_model.model.layers.37.block_sparse_moe.gate",
|
| 413 |
-
"language_model.model.layers.37.self_attn.index_k_proj",
|
| 414 |
-
"language_model.model.layers.37.self_attn.index_q_proj",
|
| 415 |
"language_model.model.layers.38.block_sparse_moe.gate",
|
| 416 |
-
"language_model.model.layers.38.self_attn.index_k_proj",
|
| 417 |
-
"language_model.model.layers.38.self_attn.index_q_proj",
|
| 418 |
"language_model.model.layers.39.block_sparse_moe.gate",
|
| 419 |
-
"language_model.model.layers.39.self_attn.index_k_proj",
|
| 420 |
-
"language_model.model.layers.39.self_attn.index_q_proj",
|
| 421 |
"language_model.model.layers.4.block_sparse_moe.gate",
|
| 422 |
-
"language_model.model.layers.4.self_attn.index_k_proj",
|
| 423 |
-
"language_model.model.layers.4.self_attn.index_q_proj",
|
| 424 |
"language_model.model.layers.40.block_sparse_moe.gate",
|
| 425 |
-
"language_model.model.layers.40.self_attn.index_k_proj",
|
| 426 |
-
"language_model.model.layers.40.self_attn.index_q_proj",
|
| 427 |
"language_model.model.layers.41.block_sparse_moe.gate",
|
| 428 |
-
"language_model.model.layers.41.self_attn.index_k_proj",
|
| 429 |
-
"language_model.model.layers.41.self_attn.index_q_proj",
|
| 430 |
"language_model.model.layers.42.block_sparse_moe.gate",
|
| 431 |
-
"language_model.model.layers.42.self_attn.index_k_proj",
|
| 432 |
-
"language_model.model.layers.42.self_attn.index_q_proj",
|
| 433 |
"language_model.model.layers.43.block_sparse_moe.gate",
|
| 434 |
-
"language_model.model.layers.43.self_attn.index_k_proj",
|
| 435 |
-
"language_model.model.layers.43.self_attn.index_q_proj",
|
| 436 |
"language_model.model.layers.44.block_sparse_moe.gate",
|
| 437 |
-
"language_model.model.layers.44.self_attn.index_k_proj",
|
| 438 |
-
"language_model.model.layers.44.self_attn.index_q_proj",
|
| 439 |
"language_model.model.layers.45.block_sparse_moe.gate",
|
| 440 |
-
"language_model.model.layers.45.self_attn.index_k_proj",
|
| 441 |
-
"language_model.model.layers.45.self_attn.index_q_proj",
|
| 442 |
"language_model.model.layers.46.block_sparse_moe.gate",
|
| 443 |
-
"language_model.model.layers.46.self_attn.index_k_proj",
|
| 444 |
-
"language_model.model.layers.46.self_attn.index_q_proj",
|
| 445 |
"language_model.model.layers.47.block_sparse_moe.gate",
|
| 446 |
-
"language_model.model.layers.47.self_attn.index_k_proj",
|
| 447 |
-
"language_model.model.layers.47.self_attn.index_q_proj",
|
| 448 |
"language_model.model.layers.48.block_sparse_moe.gate",
|
| 449 |
-
"language_model.model.layers.48.self_attn.index_k_proj",
|
| 450 |
-
"language_model.model.layers.48.self_attn.index_q_proj",
|
| 451 |
"language_model.model.layers.49.block_sparse_moe.gate",
|
| 452 |
-
"language_model.model.layers.49.self_attn.index_k_proj",
|
| 453 |
-
"language_model.model.layers.49.self_attn.index_q_proj",
|
| 454 |
"language_model.model.layers.5.block_sparse_moe.gate",
|
| 455 |
-
"language_model.model.layers.5.self_attn.index_k_proj",
|
| 456 |
-
"language_model.model.layers.5.self_attn.index_q_proj",
|
| 457 |
"language_model.model.layers.50.block_sparse_moe.gate",
|
| 458 |
-
"language_model.model.layers.50.self_attn.index_k_proj",
|
| 459 |
-
"language_model.model.layers.50.self_attn.index_q_proj",
|
| 460 |
"language_model.model.layers.51.block_sparse_moe.gate",
|
| 461 |
-
"language_model.model.layers.51.self_attn.index_k_proj",
|
| 462 |
-
"language_model.model.layers.51.self_attn.index_q_proj",
|
| 463 |
"language_model.model.layers.52.block_sparse_moe.gate",
|
| 464 |
-
"language_model.model.layers.52.self_attn.index_k_proj",
|
| 465 |
-
"language_model.model.layers.52.self_attn.index_q_proj",
|
| 466 |
"language_model.model.layers.53.block_sparse_moe.gate",
|
| 467 |
-
"language_model.model.layers.53.self_attn.index_k_proj",
|
| 468 |
-
"language_model.model.layers.53.self_attn.index_q_proj",
|
| 469 |
"language_model.model.layers.54.block_sparse_moe.gate",
|
| 470 |
-
"language_model.model.layers.54.self_attn.index_k_proj",
|
| 471 |
-
"language_model.model.layers.54.self_attn.index_q_proj",
|
| 472 |
"language_model.model.layers.55.block_sparse_moe.gate",
|
| 473 |
-
"language_model.model.layers.55.self_attn.index_k_proj",
|
| 474 |
-
"language_model.model.layers.55.self_attn.index_q_proj",
|
| 475 |
"language_model.model.layers.56.block_sparse_moe.gate",
|
| 476 |
-
"language_model.model.layers.56.self_attn.index_k_proj",
|
| 477 |
-
"language_model.model.layers.56.self_attn.index_q_proj",
|
| 478 |
"language_model.model.layers.57.block_sparse_moe.gate",
|
| 479 |
-
"language_model.model.layers.57.self_attn.index_k_proj",
|
| 480 |
-
"language_model.model.layers.57.self_attn.index_q_proj",
|
| 481 |
"language_model.model.layers.58.block_sparse_moe.gate",
|
| 482 |
-
"language_model.model.layers.58.self_attn.index_k_proj",
|
| 483 |
-
"language_model.model.layers.58.self_attn.index_q_proj",
|
| 484 |
"language_model.model.layers.59.block_sparse_moe.gate",
|
| 485 |
-
"language_model.model.layers.59.self_attn.index_k_proj",
|
| 486 |
-
"language_model.model.layers.59.self_attn.index_q_proj",
|
| 487 |
"language_model.model.layers.6.block_sparse_moe.gate",
|
| 488 |
-
"language_model.model.layers.6.self_attn.index_k_proj",
|
| 489 |
-
"language_model.model.layers.6.self_attn.index_q_proj",
|
| 490 |
"language_model.model.layers.7.block_sparse_moe.gate",
|
| 491 |
-
"language_model.model.layers.7.self_attn.index_k_proj",
|
| 492 |
-
"language_model.model.layers.7.self_attn.index_q_proj",
|
| 493 |
"language_model.model.layers.8.block_sparse_moe.gate",
|
| 494 |
-
"language_model.model.layers.8.self_attn.index_k_proj",
|
| 495 |
-
"language_model.model.layers.8.self_attn.index_q_proj",
|
| 496 |
"language_model.model.layers.9.block_sparse_moe.gate",
|
| 497 |
-
"language_model.model.layers.9.self_attn.index_k_proj",
|
| 498 |
-
"language_model.model.layers.9.self_attn.index_q_proj",
|
| 499 |
"multi_modal_projector.linear_1",
|
| 500 |
"multi_modal_projector.linear_2",
|
| 501 |
"patch_merge_mlp.linear_1",
|
|
@@ -807,7 +702,7 @@
|
|
| 807 |
"kv_cache_quant_config": {},
|
| 808 |
"kv_cache_post_rope": false,
|
| 809 |
"quant_mode": "eager_mode",
|
| 810 |
-
"version": "0.12+
|
| 811 |
"export": {
|
| 812 |
"kv_cache_group": [],
|
| 813 |
"min_kv_scale": 0.0,
|
|
|
|
| 325 |
},
|
| 326 |
"exclude": [
|
| 327 |
"language_model.lm_head",
|
| 328 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 329 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 331 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 332 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 333 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 334 |
"language_model.model.layers.10.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 335 |
"language_model.model.layers.11.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 336 |
"language_model.model.layers.12.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 337 |
"language_model.model.layers.13.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 338 |
"language_model.model.layers.14.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 339 |
"language_model.model.layers.15.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 340 |
"language_model.model.layers.16.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 341 |
"language_model.model.layers.17.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 342 |
"language_model.model.layers.18.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 343 |
"language_model.model.layers.19.block_sparse_moe.gate",
|
| 344 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 345 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 347 |
"language_model.model.layers.20.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 348 |
"language_model.model.layers.21.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 349 |
"language_model.model.layers.22.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 350 |
"language_model.model.layers.23.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 351 |
"language_model.model.layers.24.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 352 |
"language_model.model.layers.25.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 353 |
"language_model.model.layers.26.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 354 |
"language_model.model.layers.27.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 355 |
"language_model.model.layers.28.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 356 |
"language_model.model.layers.29.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 357 |
"language_model.model.layers.3.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 358 |
"language_model.model.layers.30.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 359 |
"language_model.model.layers.31.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 360 |
"language_model.model.layers.32.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 361 |
"language_model.model.layers.33.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 362 |
"language_model.model.layers.34.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 363 |
"language_model.model.layers.35.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 364 |
"language_model.model.layers.36.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 365 |
"language_model.model.layers.37.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 366 |
"language_model.model.layers.38.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 367 |
"language_model.model.layers.39.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 368 |
"language_model.model.layers.4.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 369 |
"language_model.model.layers.40.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 370 |
"language_model.model.layers.41.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 371 |
"language_model.model.layers.42.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 372 |
"language_model.model.layers.43.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 373 |
"language_model.model.layers.44.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 374 |
"language_model.model.layers.45.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 375 |
"language_model.model.layers.46.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 376 |
"language_model.model.layers.47.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 377 |
"language_model.model.layers.48.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 378 |
"language_model.model.layers.49.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 379 |
"language_model.model.layers.5.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 380 |
"language_model.model.layers.50.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 381 |
"language_model.model.layers.51.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 382 |
"language_model.model.layers.52.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 383 |
"language_model.model.layers.53.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 384 |
"language_model.model.layers.54.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 385 |
"language_model.model.layers.55.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 386 |
"language_model.model.layers.56.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 387 |
"language_model.model.layers.57.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 388 |
"language_model.model.layers.58.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 389 |
"language_model.model.layers.59.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 390 |
"language_model.model.layers.6.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 391 |
"language_model.model.layers.7.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 392 |
"language_model.model.layers.8.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 393 |
"language_model.model.layers.9.block_sparse_moe.gate",
|
|
|
|
|
|
|
| 394 |
"multi_modal_projector.linear_1",
|
| 395 |
"multi_modal_projector.linear_2",
|
| 396 |
"patch_merge_mlp.linear_1",
|
|
|
|
| 702 |
"kv_cache_quant_config": {},
|
| 703 |
"kv_cache_post_rope": false,
|
| 704 |
"quant_mode": "eager_mode",
|
| 705 |
+
"version": "0.12+5684ef6391b",
|
| 706 |
"export": {
|
| 707 |
"kv_cache_group": [],
|
| 708 |
"min_kv_scale": 0.0,
|
figures/benchmark.jpeg
ADDED
|
Git LFS Details
|
figures/efficiency_gqa_vs_msa.png
ADDED
|
figures/logo.svg
ADDED
|
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 200019,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 200020,
|
| 5 |
+
"temperature": 1.0,
|
| 6 |
+
"top_p": 0.95,
|
| 7 |
+
"transformers_version": "4.46.1"
|
| 8 |
+
}
|
model-00001-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbfdba9b4241f6455037ab50c79cc7937e4fffc762dbf4911f9bad5ce70e37c8
|
| 3 |
+
size 5476813528
|
model-00002-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0f2c893ae5430467b1b7a369e71e2e9e69b0bd996d00b0643ff99dbb7a69aec
|
| 3 |
+
size 3666991696
|
model-00003-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea1684d2e3ca216023e655563f1dea069d950ffd1317261fe649840695612e65
|
| 3 |
+
size 4325592160
|
model-00004-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e2c6f38479783138b0753d30bf876e16f57f7d579553ec491680b971a06d182
|
| 3 |
+
size 4325592152
|
model-00005-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66b0f2487146b6cbfd0e770f0ca0230f76e63f22b1018f4793039a7749dc9d42
|
| 3 |
+
size 4325592152
|
model-00006-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25a67e5f4d06c60afdabc9c390093b9005fd186e79050a6e88c2f289e2e77b09
|
| 3 |
+
size 4325592152
|
model-00007-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff993fdd56ece5a1dd7ccf4707ae9b52fe9b60533c99a8c6d7d9337899b66160
|
| 3 |
+
size 4325592152
|
model-00008-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f33415b2afa537e835cedd5844970773ddbdca5ce3c4fbdfabf152be40eb7a51
|
| 3 |
+
size 4325592152
|
model-00009-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb18683fc6361dc6a41ebea1888d21529d3f8d8d9d1562f59fdef94077549adc
|
| 3 |
+
size 4325592152
|
model-00010-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:474004dbd736515d2ed03b81225eba4b80e262180777f3b61a4623233ac8172f
|
| 3 |
+
size 4325592952
|
model-00011-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcd3419bfb98b43fae13be9ac43117adfaa2776237ef94f34be55c05220ce270
|
| 3 |
+
size 4325592952
|
model-00012-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e01e8085ce34f787c1db8e15036b3eab2395be9ba043b9f06d9508cf66203716
|
| 3 |
+
size 4325592952
|
model-00013-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac6bef8d73f9621545210c3dfb7942227d0138d71486636864b530ee302d7f87
|
| 3 |
+
size 4325592952
|
model-00014-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4651bcde0da735519a824afb3b08145a73fa094c80510715121669953c777e1
|
| 3 |
+
size 4325592952
|
model-00015-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:986d278785f7cdaac8fb6e01fb4569f01429ce4d6355ede542d433e9308c9127
|
| 3 |
+
size 4325592952
|
model-00016-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2046ebd3c5e78411e940c8dc2d7ca770120def6b35c430e41b1117f89d7166d5
|
| 3 |
+
size 4325592952
|
model-00017-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dfbaa5685f4da3e04f348232b9fa02d8c57875e984d2b0101fae3103b53bf9d
|
| 3 |
+
size 4325592952
|
model-00018-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20dab737f65564f5d874d144ae9509c14e85649e8a40281ebb734b0d01c10bd2
|
| 3 |
+
size 4325592952
|
model-00019-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b6d4f78e097843243ddde5564a5528dbe288a5219a8f4e2f1f2a205eee06c67
|
| 3 |
+
size 4325592952
|
model-00020-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8b2d0241d627fe373a0d5faadf2d94ce7dd83cefb9983715082588ae81475f3
|
| 3 |
+
size 4325592952
|
model-00021-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a09a7d9b0d377014af4ca32674e826d4516e88063f7d438ca45b3bf5500ddf52
|
| 3 |
+
size 4325592952
|
model-00022-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75be1f95230f254577723ddb692238d363f8be720569168b4ec9c13a9816baed
|
| 3 |
+
size 4325592952
|
model-00023-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf68eef99b975f550fa872c3b50b364b88269b489dcdf9b4280c8d3667fd4343
|
| 3 |
+
size 4325592952
|
model-00024-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b10e28ce8bab36f2852604a01b871f8a38d2f0401632ada99557f31248e3ee66
|
| 3 |
+
size 4325592952
|
model-00025-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7459a9bf592c2b294ed3f21fe43f9f31ea5d2bc68417e6989389f467b4d0e373
|
| 3 |
+
size 1447755632
|
model-00026-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a06f375b49a832da777126b930b60e7320445692d6b70d0905885a9326e4da76
|
| 3 |
+
size 4463442560
|
model-00027-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3550bbbfcada827aa265bca57d1de8f6d0b7965c27939bd952939700a9de2e7
|
| 3 |
+
size 3994691280
|
model-00028-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ca9f10ad0d2ad90e97930bf84c348342ae25ddf85bf8014c28afc2b14400f78
|
| 3 |
+
size 3994691280
|
model-00029-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff0479228ca1d3db91294bb48107a4787dda8ee65f40a163a8d577b21b41c4f5
|
| 3 |
+
size 3994691280
|
model-00030-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6891271851b125edf756cf8b2b0f0c30bd8d6b4fe52a5cd9d8b51114715d7ecf
|
| 3 |
+
size 3994691280
|
model-00031-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c83d0dc28bf4be1d563aa362ce5a61a4da585f8b6a21fe486eec19db5588d533
|
| 3 |
+
size 3994691280
|
model-00032-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad84178fe8cec77cffecc6d7e7454d8402fc64536bd0975f89db5cef5aab786a
|
| 3 |
+
size 3994691280
|
model-00033-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59be31958ff479ef40f6528ec282072bbe6df07c458040d4961810d06170b006
|
| 3 |
+
size 3994691280
|
model-00034-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6704ccab30a79faad151e3716990d3772892126d238072b8648be3ed5f4ea844
|
| 3 |
+
size 3994691280
|
model-00035-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:100436d8f1c228be17f218dae892a3a60494663b64eb71e8bdfc02fbe8446b8f
|
| 3 |
+
size 3994691280
|
model-00036-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d5f30f3fb8bfd7a53f3bcfea61e764a77879d214ce51f27ffa804b6f25abadb
|
| 3 |
+
size 3994691280
|
model-00037-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7b6c29e0e21a6606701cfbecd1d86d2e1e897d4240f0cefcef0ac2a2fdab759
|
| 3 |
+
size 3663789616
|
model-00038-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6269388ea6c860bac35be360ae3d51df282d5927942f072c1baa105ca7713758
|
| 3 |
+
size 3663789616
|
model-00039-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fa39d118cede26107338f256ebb07dda4aadce79607d0ef766d66d4636c2946
|
| 3 |
+
size 3663789616
|
model-00040-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aa857db4d018a49342d62d94a9329c9abd513c48dd23c450139d5fa13fdcb17
|
| 3 |
+
size 3663789616
|
model-00041-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ba983919827eb2d71c935be25af68508ae320ff77660c225dcab401e878106c
|
| 3 |
+
size 3663789616
|
model-00042-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a329a325cb8a092fd89a0f902aefc8c06d0d46df8f839de2d7935fe06c48c7b8
|
| 3 |
+
size 3663789616
|
model-00043-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7ea7db06a1d7d92bd774aae395a98003a7b871b8bf75e6cb0b6c5847994cf5c
|
| 3 |
+
size 3663789616
|
model-00044-of-00059.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48d0b38b7dfad546c733723e408580023196a09949918806eb614f15ca210869
|
| 3 |
+
size 3663789616
|