423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-07-31 10:42:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] add support for Falcon H1 (#8403)

Browse Source
This commit is contained in:
Dhia Eddine Rhaiem 2025-06-18 12:51:23 +04:00 committed by GitHub
parent 0e1fea71d2
commit 0d7d0ea972
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 69 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -262,6 +262,7 @@ Choose your path:
| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai) | 236B/671B | deepseek3 |
| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai) | 1.5B/7B/8B/14B/32B/70B/671B | deepseekr1 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Falcon-H1](https://huggingface.co/tiiuae) | 0.5B/1.5B/3B/7B/34B | falcon_h1 |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3/gemma (1B) |
| [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/THUDM) | 9B/32B | glm4/glmz1 |

13
src/llamafactory/data/template.py
View File

@ -916,6 +916,19 @@ register_template(
)
register_template(
name="falcon_h1",
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n"]),
format_assistant=StringFormatter(slots=["{{content}}<|im_end|>\n"]),
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
format_function=FunctionFormatter(slots=["{{content}}<|im_end|>\n"], tool_format="default"),
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n"]),
format_tools=ToolFormatter(tool_format="default"),
format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
stop_words=["<|im_end|>", "<|end_of_text|>"],
)
register_template(
name="fewshot",
format_assistant=StringFormatter(slots=["{{content}}\n\n"]),

55
src/llamafactory/extras/constants.py
View File

@ -633,6 +633,61 @@ register_model_group(
template="falcon",
)
register_model_group(
models={
"Falcon-H1-0.5B-Instruct": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-0.5B-Instruct",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-0.5B-Instruct",
},
"Falcon-H1-0.5B-Base": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-0.5B-Base",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-0.5B-Base",
},
"Falcon-H1-1.5B-Instruct": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-1.5B-Instruct",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Instruct",
},
"Falcon-H1-1.5B-Base": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-1.5B-Base",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Base",
},
"Falcon-H1-1.5B-Deep-Instruct": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-1.5B-Deep-Instruct",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Deep-Instruct",
},
"Falcon-H1-1.5B-Deep-Base": {
DownloadSource.DEFAULT: "tiuae/Falcon-H1-1.5B-Deep-Base",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Deep-Base",
},
"Falcon-H1-3B-Instruct": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-3B-Instruct",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-3B-Instruct",
},
"Falcon-H1-3B-Base": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-3B-Base",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-3B-Base",
},
"Falcon-H1-7B-Instruct": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-7B-Instruct",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-7B-Instruct",
},
"Falcon-H1-7B-Base": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-7B-Base",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-7B-Base",
},
"Falcon-H1-34B-Instruct": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-34B-Instruct",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-34B-Instruct",
},
"Falcon-H1-34B-Base": {
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-34B-Base",
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-34B-Base",
},
},
template="falcon_h1",
)
register_model_group(
models={