ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'hiyouga:main' into main

Browse Source 
Former-commit-id: 1f3163509ecd05902ea216a905b4ca15ddd3696f
This commit is contained in:
BUAADreamer
2024-05-09 13:45:43 +08:00
committed by GitHub
parent 172600d432 4ce4172c87
commit 47892418ad
6 changed files with 20 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -324,6 +324,14 @@ register_model_group(
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
},
"DeepSeek-MoE-236B": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2",
},
"DeepSeek-MoE-236B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2-Chat",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2-Chat",
},
},
template="deepseek",
)
@@ -569,6 +577,10 @@ register_model_group(
DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-70B-Instruct",
DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3-70B-Instruct",
},
"LLaMA3-8B-Chinese-Chat": {
DownloadSource.DEFAULT: "shenzhi-wang/Llama3-8B-Chinese-Chat",
DownloadSource.MODELSCOPE: "LLM-Research/Llama3-8B-Chinese-Chat",
},
},
template="llama3",
)

4
src/llmtuner/model/utils/valuehead.py
View File

@@ -57,3 +57,7 @@ def prepare_valuehead_model(model: "PreTrainedModel") -> None:
if getattr(model.config, "model_type", None) == "chatglm":
setattr(model, "lm_head", model.transformer.output_layer)
setattr(model, "_keys_to_ignore_on_save", ["lm_head.weight"])
if getattr(model.config, "model_type", None) == "internlm2":
setattr(model, "lm_head", model.output)
setattr(model, "_keys_to_ignore_on_save", ["lm_head.weight"])