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

Merge pull request #5547 from marko1616/chore/llama3.2 

Chore: Support llama3.2.
This commit is contained in:
hoshi-hiyouga 2024-09-26 11:38:34 +08:00 committed by GitHub
parent 46e2c1ea9f 8e5d12c2c4
commit 6b62550af1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 25 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -175,7 +175,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 | | [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 |
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - | | [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 | | [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |
| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama) | 8B/70B | llama3 | | [Llama 3/Llama 3.1/Llama3.2](https://huggingface.co/meta-llama) | 1B/3B/8B/70B | llama3 |
| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava | | [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava |
| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B/4B | cpm/cpm3 | | [MiniCPM](https://huggingface.co/openbmb) | 1B/2B/4B | cpm/cpm3 |
| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | | [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral |

2
README_zh.md
View File

@ -176,7 +176,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 | | [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 |
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - | | [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 | | [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |
| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama) | 8B/70B | llama3 | | [Llama 3/Llama 3.1/Llama3.2](https://huggingface.co/meta-llama) | 1B/3B/8B/70B | llama3 |
| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava | | [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava |
| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B/4B | cpm/cpm3 | | [MiniCPM](https://huggingface.co/openbmb) | 1B/2B/4B | cpm/cpm3 |
| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral | | [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral |

23
src/llamafactory/extras/constants.py
View File

@ -798,6 +798,29 @@ register_model_group(
) )
register_model_group(
models={
"LLaMA3.2-1B": {
DownloadSource.DEFAULT: "meta-llama/Llama-3.2-1B",
DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-1B",
},
"LLaMA3.2-3B": {
DownloadSource.DEFAULT: "meta-llama/Llama-3.2-3B",
DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-3B",
},
"LLaMA3.2-1B-Instruct": {
DownloadSource.DEFAULT: "meta-llama/Llama-3.2-1B-Instruct",
DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-1B-Instruct",
},
"LLaMA3.2-3B-Instruct": {
DownloadSource.DEFAULT: "meta-llama/Llama-3.2-3B-Instruct",
DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-3B-Instruct",
},
},
template="llama3",
)
register_model_group( register_model_group(
models={ models={
"LLaVA1.5-7B-Chat": { "LLaVA1.5-7B-Chat": {