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

[model] add seed coder and qwen3 quant models (#8039)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-05-13 15:59:55 +08:00
committed by GitHub
parent 68fc068cab
commit dc080399c6
11 changed files with 94 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -887,12 +887,13 @@ register_model_group(
register_model_group(
models={
"Granite-3.2-1B-A400M-Base": {
"Granite-Vision-3.2-2B": {
DownloadSource.DEFAULT: "ibm-granite/granite-vision-3.2-2b",
DownloadSource.MODELSCOPE: "AI-ModelScope/granite-vision-3.2-2b",
},
},
template="granite3_vision",
multimodal=True,
)
@@ -2502,6 +2503,22 @@ register_model_group(
DownloadSource.DEFAULT: "Qwen/Qwen3-235B-A22B",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-235B-A22B",
},
"Qwen3-0.6B-Instruct-GPTQ-Int8": {
DownloadSource.DEFAULT: "Qwen/Qwen3-0.6B-GPTQ-Int8",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-0.6B-GPTQ-Int8",
},
"Qwen3-1.7B-Instruct-GPTQ-Int8": {
DownloadSource.DEFAULT: "Qwen/Qwen3-1.7B-GPTQ-Int8",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-1.7B-GPTQ-Int8",
},
"Qwen3-4B-Instruct-AWQ": {
DownloadSource.DEFAULT: "Qwen/Qwen3-4B-AWQ",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-4B-AWQ",
},
"Qwen3-8B-Instruct-AWQ": {
DownloadSource.DEFAULT: "Qwen/Qwen3-8B-AWQ",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-8B-AWQ",
},
"Qwen3-14B-Instruct-AWQ": {
DownloadSource.DEFAULT: "Qwen/Qwen3-14B-AWQ",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-14B-AWQ",
@@ -2510,6 +2527,14 @@ register_model_group(
DownloadSource.DEFAULT: "Qwen/Qwen3-32B-AWQ",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-32B-AWQ",
},
"Qwen3-30B-A3B-Instruct-GPTQ-Int4": {
DownloadSource.DEFAULT: "Qwen/Qwen3-30B-A3B-GPTQ-Int4",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-30B-A3B-GPTQ-Int4",
},
"Qwen3-235B-A22B-Instruct-GPTQ-Int4": {
DownloadSource.DEFAULT: "Qwen/Qwen3-235B-A22B-GPTQ-Int4",
DownloadSource.MODELSCOPE: "Qwen/Qwen3-235B-A22B-GPTQ-Int4",
},
},
template="qwen3",
)
@@ -2651,15 +2676,17 @@ register_model_group(
register_model_group(
models={
"SOLAR-10.7B-v1.0": {
DownloadSource.DEFAULT: "upstage/SOLAR-10.7B-v1.0",
"Seed-Coder-8B-Base": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-Coder-8B-Base",
},
"SOLAR-10.7B-Instruct-v1.0": {
DownloadSource.DEFAULT: "upstage/SOLAR-10.7B-Instruct-v1.0",
DownloadSource.MODELSCOPE: "AI-ModelScope/SOLAR-10.7B-Instruct-v1.0",
"Seed-Coder-8B-Instruct": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-Coder-8B-Instruct",
},
"Seed-Coder-8B-Instruct-Reasoning": {
DownloadSource.DEFAULT: "ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16",
},
},
template="solar",
template="seed_coder",
)
@@ -2684,6 +2711,20 @@ register_model_group(
)
register_model_group(
models={
"SOLAR-10.7B-v1.0": {
DownloadSource.DEFAULT: "upstage/SOLAR-10.7B-v1.0",
},
"SOLAR-10.7B-Instruct-v1.0": {
DownloadSource.DEFAULT: "upstage/SOLAR-10.7B-Instruct-v1.0",
DownloadSource.MODELSCOPE: "AI-ModelScope/SOLAR-10.7B-Instruct-v1.0",
},
},
template="solar",
)
register_model_group(
models={
"StarCoder2-3B": {