423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 06:12:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

support Yi-Coder models

Browse Source 
Former-commit-id: 359ef8bb0ebb8ccf9651ac2b737c5a705dab6bad
This commit is contained in:
hiyouga 2024-09-05 03:12:24 +08:00
parent 666013d09d
commit 4fccc65579
4 changed files with 16 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -185,7 +185,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B | qwen2_vl |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |
| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse |
| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi |
| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai) | 1.5B/6B/9B/34B | yi |
| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl |
| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan |

2
README_zh.md
View File

@ -186,7 +186,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
| [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B | qwen2_vl |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |
| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse |
| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi |
| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai) | 1.5B/6B/9B/34B | yi |
| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl |
| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan |

4
src/llamafactory/data/mm_plugin.py
View File

@ -105,7 +105,7 @@ def _get_mm_inputs(
It holds num_patches == torch.prod(image_grid_thw)
"""
image_processor: "BaseImageProcessor" = getattr(processor, "image_processor")
input_dict = {"images": None, "videos": None}
input_dict = {"images": None} # default key
if len(images) != 0:
images = _regularize_images(images, processor)
input_dict["images"] = images
@ -114,7 +114,7 @@ def _get_mm_inputs(
videos = _regularize_videos(videos, processor)
input_dict["videos"] = videos
if input_dict["images"] is not None or input_dict["videos"] is not None:
if input_dict.get("images", None) is not None or input_dict.get("videos", None) is not None:
return image_processor(**input_dict, return_tensors="pt")
else:
return {}

12
src/llamafactory/extras/constants.py
View File

@ -1633,6 +1633,18 @@ register_model_group(
DownloadSource.DEFAULT: "01-ai/Yi-1.5-34B-Chat",
DownloadSource.MODELSCOPE: "01ai/Yi-1.5-34B-Chat",
},
"Yi-Coder-1.5B": {
DownloadSource.DEFAULT: "01-ai/Yi-Coder-1.5B",
},
"Yi-Coder-9B": {
DownloadSource.DEFAULT: "01-ai/Yi-Coder-9B",
},
"Yi-Coder-1.5B-Chat": {
DownloadSource.DEFAULT: "01-ai/Yi-Coder-1.5B-Chat",
},
"Yi-Coder-9B-Chat": {
DownloadSource.DEFAULT: "01-ai/Yi-Coder-9B-Chat",
},
},
template="yi",
)