423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 22:32:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix some errors due to inconsistency of model cards

Browse Source 
Former-commit-id: 2166b9bc6ba35760ff85b63620af9fa0213a4c78
This commit is contained in:
Kingsley 2024-09-30 19:58:34 +08:00
parent 4f85098088
commit 94ce8f561f
5 changed files with 66 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -163,7 +163,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
## Supported Models
| Model | Model size | Template |
| ----------------------------------------------------------------- | -------------------------------- | ---------------- |
|-------------------------------------------------------------| -------------------------------- | ---------------- |
| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 |
| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - |
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
@ -185,7 +185,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [PaliGemma](https://huggingface.co/google) | 3B | paligemma |
| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - |
| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi |
| [Pixtral](https://huggingface.co/mistral-community/pixtral-12b) | 12B | pixtral |
| [Pixtral](https://huggingface.co/mistral-community) | 12B | pixtral |
| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen |
| [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B/72B | qwen2_vl |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |

4
README_zh.md
View File

@ -164,7 +164,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
## 模型
| 模型名 | 模型大小 | Template |
| ----------------------------------------------------------------- | -------------------------------- | ---------------- |
|-------------------------------------------------------------| -------------------------------- | ---------------- |
| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 |
| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - |
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
@ -186,7 +186,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
| [PaliGemma](https://huggingface.co/google) | 3B | paligemma |
| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - |
| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi |
| [Pixtral](https://huggingface.co/mistral-community/pixtral-12b) | 12B | pixtral |
| [Pixtral](https://huggingface.co/mistral-community) | 12B | pixtral |
| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen |
| [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B/72B | qwen2_vl |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |

4
src/llamafactory/extras/constants.py
View File

@ -1164,12 +1164,12 @@ register_model_group(
register_model_group(
models={
"Pixtral-12B": {
"Pixtral-12B-Instruct": {
DownloadSource.DEFAULT: "mistral-community/pixtral-12b",
DownloadSource.MODELSCOPE: "AI-ModelScope/pixtral-12b",
}
},
template="mistral",
template="pixtral",
vision=True
)

5
src/llamafactory/model/model_utils/visual.py
View File

@ -92,12 +92,10 @@ def autocast_projector_dtype(model: "PreTrainedModel", model_args: "ModelArgumen
if getattr(model, "quantization_method", None):
model_type = getattr(model.config, "model_type", None)
if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "pixtral", "video_llava"]:
mm_projector: "torch.nn.Module" = getattr(model, "multi_modal_projector")
elif model_type == "qwen2_vl":
mm_projector: "torch.nn.Module" = getattr(getattr(model, "visual"), "merger")
elif model_type == "pixtral":
mm_projector: "torch.nn.Module" = getattr(model, "vision_language_adapte")
else:
return
@ -133,7 +131,6 @@ def get_forbidden_modules(config: "PretrainedConfig", finetuning_args: "Finetuni
if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "pixtral", "video_llava"]:
if finetuning_args.freeze_vision_tower:
forbidden_modules.add("vision_tower")
forbidden_modules.add("vision_encoder")
if finetuning_args.train_mm_proj_only:
forbidden_modules.add("language_model")