423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-17 20:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] add mistral small models (#6786)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-02-01 04:31:38 +08:00
committed by GitHub
parent 999c7c8fe0
commit 94803d8133
10 changed files with 106 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
src/llamafactory/extras/constants.py
View File

@@ -1201,23 +1201,44 @@ register_model_group(
register_model_group(
models={
"MiniCPM-o-2_6-Chat": {
"MiniCPM-o-2_6": {
DownloadSource.DEFAULT: "openbmb/MiniCPM-o-2_6",
DownloadSource.MODELSCOPE: "OpenBMB/MiniCPM-o-2_6",
},
},
template="minicpm_v",
vision=True,
)
register_model_group(
models={
"MiniCPM-V-2_6-Chat": {
"MiniCPM-V-2_6": {
DownloadSource.DEFAULT: "openbmb/MiniCPM-V-2_6",
DownloadSource.MODELSCOPE: "OpenBMB/MiniCPM-V-2_6",
},
},
template="minicpm_v",
vision=True,
)
register_model_group(
models={
"Ministral-8B-Instruct-2410": {
DownloadSource.DEFAULT: "mistralai/Ministral-8B-Instruct-2410",
DownloadSource.MODELSCOPE: "mistralai/Ministral-8B-Instruct-2410",
},
"Mistral-Nemo-Base-2407": {
DownloadSource.DEFAULT: "mistralai/Mistral-Nemo-Base-2407",
DownloadSource.MODELSCOPE: "LLM-Research/Mistral-Nemo-Base-2407",
},
"Mistral-Nemo-Instruct-2407": {
DownloadSource.DEFAULT: "mistralai/Mistral-Nemo-Instruct-2407",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-Nemo-Instruct-2407",
},
},
template="ministral",
)
@@ -1227,48 +1248,60 @@ register_model_group(
DownloadSource.DEFAULT: "mistralai/Mistral-7B-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-v0.1",
},
"Mistral-7B-Instruct-v0.1": {
DownloadSource.DEFAULT: "mistralai/Mistral-7B-Instruct-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-Instruct-v0.1",
},
"Mistral-7B-v0.2": {
DownloadSource.DEFAULT: "alpindale/Mistral-7B-v0.2-hf",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-v0.2-hf",
},
"Mistral-7B-v0.3": {
DownloadSource.DEFAULT: "mistralai/Mistral-7B-v0.3",
DownloadSource.MODELSCOPE: "LLM-Research/mistral-7b-v0.3",
},
"Mistral-7B-Instruct-v0.1": {
DownloadSource.DEFAULT: "mistralai/Mistral-7B-Instruct-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-Instruct-v0.1",
},
"Mistral-7B-Instruct-v0.2": {
DownloadSource.DEFAULT: "mistralai/Mistral-7B-Instruct-v0.2",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-7B-Instruct-v0.2",
},
"Mistral-7B-v0.3": {
DownloadSource.DEFAULT: "mistralai/Mistral-7B-v0.3",
},
"Mistral-7B-Instruct-v0.3": {
DownloadSource.DEFAULT: "mistralai/Mistral-7B-Instruct-v0.3",
DownloadSource.MODELSCOPE: "LLM-Research/Mistral-7B-Instruct-v0.3",
},
"Mistral-Nemo-Instruct-2407": {
DownloadSource.DEFAULT: "mistralai/Mistral-Nemo-Instruct-2407",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mistral-Nemo-Instruct-2407",
},
},
template="mistral",
)
register_model_group(
models={
"Mistral-Small-24B-Base-2501": {
DownloadSource.DEFAULT: "mistralai/Mistral-Small-24B-Base-2501",
DownloadSource.MODELSCOPE: "mistralai/Mistral-Small-24B-Base-2501",
},
"Mistral-Small-24B-Instruct-2501": {
DownloadSource.DEFAULT: "mistralai/Mistral-Small-24B-Instruct-2501",
DownloadSource.MODELSCOPE: "mistralai/Mistral-Small-24B-Instruct-2501",
},
},
template="mistral_small",
)
register_model_group(
models={
"Mixtral-8x7B-v0.1": {
DownloadSource.DEFAULT: "mistralai/Mixtral-8x7B-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mixtral-8x7B-v0.1",
},
"Mixtral-8x7B-v0.1-Instruct": {
DownloadSource.DEFAULT: "mistralai/Mixtral-8x7B-Instruct-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mixtral-8x7B-Instruct-v0.1",
},
"Mixtral-8x22B-v0.1": {
DownloadSource.DEFAULT: "mistralai/Mixtral-8x22B-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mixtral-8x22B-v0.1",
},
"Mixtral-8x7B-v0.1-Instruct": {
DownloadSource.DEFAULT: "mistralai/Mixtral-8x7B-Instruct-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mixtral-8x7B-Instruct-v0.1",
},
"Mixtral-8x22B-v0.1-Instruct": {
DownloadSource.DEFAULT: "mistralai/Mixtral-8x22B-Instruct-v0.1",
DownloadSource.MODELSCOPE: "AI-ModelScope/Mixtral-8x22B-Instruct-v0.1",

2
src/llamafactory/extras/misc.py
View File

@@ -94,7 +94,7 @@ def check_dependencies() -> None:
r"""
Checks the version of the required packages.
"""
check_version("transformers>=4.41.2,<=4.48.1,!=4.46.0,!=4.46.1,!=4.46.2,!=4.46.3,!=4.47.0,!=4.47.1,!=4.48.0")
check_version("transformers>=4.41.2,<=4.48.2,!=4.46.0,!=4.46.1,!=4.46.2,!=4.46.3,!=4.47.0,!=4.47.1,!=4.48.0")
check_version("datasets>=2.16.0,<=3.2.0")
check_version("accelerate>=0.34.0,<=1.2.1")
check_version("peft>=0.11.1,<=0.12.0")