423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor mm training

Browse Source
This commit is contained in:
hiyouga
2024-08-30 02:14:31 +08:00
parent 727e184840
commit 3382317e32
32 changed files with 505 additions and 472 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
src/llamafactory/extras/constants.py
View File

@@ -47,6 +47,8 @@ FILEEXT2TYPE = {
IGNORE_INDEX = -100
IMAGE_PLACEHOLDER = "<image>"
LAYERNORM_NAMES = {"norm", "ln"}
LLAMABOARD_CONFIG = "llamaboard_config.yaml"
@@ -785,7 +787,7 @@ register_model_group(
DownloadSource.DEFAULT: "llava-hf/llava-1.5-13b-hf",
},
},
template="vicuna",
template="llava",
vision=True,
)
@@ -930,27 +932,28 @@ register_model_group(
register_model_group(
models={
"PaliGemma-3B-pt-224": {
"PaliGemma-3B-pt-224-Chat": {
DownloadSource.DEFAULT: "google/paligemma-3b-pt-224",
DownloadSource.MODELSCOPE: "AI-ModelScope/paligemma-3b-pt-224",
},
"PaliGemma-3B-pt-448": {
"PaliGemma-3B-pt-448-Chat": {
DownloadSource.DEFAULT: "google/paligemma-3b-pt-448",
DownloadSource.MODELSCOPE: "AI-ModelScope/paligemma-3b-pt-448",
},
"PaliGemma-3B-pt-896": {
"PaliGemma-3B-pt-896-Chat": {
DownloadSource.DEFAULT: "google/paligemma-3b-pt-896",
DownloadSource.MODELSCOPE: "AI-ModelScope/paligemma-3b-pt-896",
},
"PaliGemma-3B-mix-224": {
"PaliGemma-3B-mix-224-Chat": {
DownloadSource.DEFAULT: "google/paligemma-3b-mix-224",
DownloadSource.MODELSCOPE: "AI-ModelScope/paligemma-3b-mix-224",
},
"PaliGemma-3B-mix-448": {
"PaliGemma-3B-mix-448-Chat": {
DownloadSource.DEFAULT: "google/paligemma-3b-mix-448",
DownloadSource.MODELSCOPE: "AI-ModelScope/paligemma-3b-mix-448",
},
},
template="paligemma",
vision=True,
)
@@ -1329,6 +1332,34 @@ register_model_group(
)
register_model_group(
models={
"Qwen2VL-2B-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-2B-Instruct",
},
"Qwen2VL-7B-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-7B-Instruct",
},
"Qwen2VL-2B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8",
},
"Qwen2VL-2B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct-AWQ",
},
"Qwen2VL-7B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8",
},
"Qwen2VL-7B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct-AWQ",
},
},
template="qwen2_vl",
vision=True,
)
register_model_group(
models={
"SOLAR-10.7B": {