From 4465e4347e9092e471fd226169b7bf30c7aaf7c2 Mon Sep 17 00:00:00 2001 From: Kingsley Date: Wed, 2 Jul 2025 15:38:38 +0800 Subject: [PATCH] [assets] update readme (#8519) --- README.md | 11 ++++++----- README_zh.md | 11 ++++++----- src/llamafactory/extras/constants.py | 6 +++++- src/llamafactory/hparams/parser.py | 2 -- 4 files changed, 17 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index cfd76f9a..6e6e2c2b 100644 --- a/README.md +++ b/README.md @@ -98,10 +98,10 @@ Choose your path: ### Day-N Support for Fine-Tuning Cutting-Edge Models -| Support Date | Model Name | -| ------------ | ------------------------------------------------------------ | -| Day 0 | Qwen3 / Qwen2.5-VL / Gemma 3 / InternLM 3 / MiniCPM-o-2.6 | -| Day 1 | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 / Llama 4 | +| Support Date | Model Name | +| ------------ | ------------------------------------------------------------------ | +| Day 0 | Qwen3 / Qwen2.5-VL / Gemma 3 / GLM4.1V / InternLM 3 / MiniCPM-o-2.6| +| Day 1 | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 / Llama 4 | ## Blogs @@ -264,8 +264,9 @@ Choose your path: | [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/gemma2 | -| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3/gemma (1B) | +| [Gemma 3/Gemma 3n](https://huggingface.co/google) | 1B/4B/6B/8B/12B/27B | gemma3(n)/gemma (1B)| | [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/THUDM) | 9B/32B | glm4/glmz1 | +| [GLM-4.1V](https://huggingface.co/THUDM) | 9B | glm4v | | [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - | | [Granite 3.0-3.3](https://huggingface.co/ibm-granite) | 1B/2B/3B/8B | granite3 | | [Hunyuan](https://huggingface.co/tencent/) | 7B | hunyuan | diff --git a/README_zh.md b/README_zh.md index 836b2ffa..ddd4df3b 100644 --- a/README_zh.md +++ b/README_zh.md @@ -100,10 +100,10 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc ### 最新模型的 Day-N 微调适配 -| 适配时间 | 模型名称 | -| ------------ | ------------------------------------------------------------ | -| Day 0 | Qwen3 / Qwen2.5-VL / Gemma 3 / InternLM 3 / MiniCPM-o-2.6 | -| Day 1 | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 / Llama 4 | +| 适配时间 | 模型名称 | +| ------------ | ------------------------------------------------------------------ | +| Day 0 | Qwen3 / Qwen2.5-VL / Gemma 3 / GLM4.1V / InternLM 3 / MiniCPM-o-2.6| +| Day 1 | Llama 3 / GLM-4 / Mistral Small / PaliGemma2 / Llama 4 | ## 官方博客 @@ -266,8 +266,9 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc | [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/gemma2 | -| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3/gemma (1B) | +| [Gemma 3/Gemma 3n](https://huggingface.co/google) | 1B/4B/6B/8B/12B/27B | gemma3(n)/gemma (1B)| | [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/THUDM) | 9B/32B | glm4/glmz1 | +| [GLM-4.1V](https://huggingface.co/THUDM) | 9B | glm4v | | [GPT-2](https://huggingface.co/openai-community) | 0.1B/0.4B/0.8B/1.5B | - | | [Granite 3.0-3.3](https://huggingface.co/ibm-granite) | 1B/2B/3B/8B | granite3 | | [Hunyuan](https://huggingface.co/tencent/) | 7B | hunyuan | diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py index 10b54813..d57115a7 100644 --- a/src/llamafactory/extras/constants.py +++ b/src/llamafactory/extras/constants.py @@ -863,7 +863,11 @@ register_model_group( "GLM-4.1V-9B-Thinking": { DownloadSource.DEFAULT: "THUDM/GLM-4.1V-9B-Thinking", DownloadSource.MODELSCOPE: "ZhipuAI/GLM-4.1V-9B-Thinking", - } + }, + "GLM-4.1V-9B-Base": { + DownloadSource.DEFAULT: "THUDM/GLM-4.1V-9B-Base", + DownloadSource.MODELSCOPE: "ZhipuAI/GLM-4.1V-9B-Base", + }, }, template="glm4v", multimodal=True, diff --git a/src/llamafactory/hparams/parser.py b/src/llamafactory/hparams/parser.py index 54becc5b..968067a1 100644 --- a/src/llamafactory/hparams/parser.py +++ b/src/llamafactory/hparams/parser.py @@ -15,7 +15,6 @@ # See the License for the specific language governing permissions and # limitations under the License. -import json import os import sys from pathlib import Path @@ -23,7 +22,6 @@ from typing import Any, Optional, Union import torch import transformers -import yaml from omegaconf import OmegaConf from transformers import HfArgumentParser from transformers.integrations import is_deepspeed_zero3_enabled