p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add Gemma2 models

This commit is contained in:
hiyouga 2024-06-28 01:26:50 +08:00
parent 2f78b5d62a
commit 6f63050e1b
4 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -160,7 +160,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [Command-R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/CodeGemma](https://huggingface.co/google) | 2B/7B | gemma |
| [Gemma/Gemma2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM4](https://huggingface.co/THUDM) | 9B | glm4 |
| [InternLM2](https://huggingface.co/internlm) | 7B/20B | intern2 |
| [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |

2
README_zh.md
View File

@ -160,7 +160,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
| [Command-R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/CodeGemma](https://huggingface.co/google) | 2B/7B | gemma |
| [Gemma/Gemma2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM4](https://huggingface.co/THUDM) | 9B | glm4 |
| [InternLM2](https://huggingface.co/internlm) | 7B/20B | intern2 |
| [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |

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

@ -507,6 +507,18 @@ register_model_group(
"Gemma-1.1-7B-Chat": {
DownloadSource.DEFAULT: "google/gemma-1.1-7b-it",
},
"Gemma-2-9B": {
DownloadSource.DEFAULT: "google/gemma-2-9b",
},
"Gemma-2-27B": {
DownloadSource.DEFAULT: "google/gemma-2-27b",
},
"Gemma-2-9B-Chat": {
DownloadSource.DEFAULT: "google/gemma-2-9b-it",
},
"Gemma-2-27B-Chat": {
DownloadSource.DEFAULT: "google/gemma-2-27b-it",
},
},
template="gemma",
)

2
src/llamafactory/train/rm/trainer.py
View File

@ -105,7 +105,7 @@ class PairwiseTrainer(Trainer):
Subclass and override to inject custom behavior.
Note that the first element will be removed from the output tuple.
See: https://github.com/huggingface/transformers/blob/v4.39.1/src/transformers/trainer.py#L3777
See: https://github.com/huggingface/transformers/blob/v4.40.0/src/transformers/trainer.py#L3842
"""
# Compute rewards
_, _, values = model(**inputs, output_hidden_states=True, return_dict=True)