opensource/self-llm
3
0
Fork 0
mirror of https://github.com/datawhalechina/self-llm.git synced 2026-08-28 23:27:40 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,395 Commits 1 Branch 0 Tags
master
Commit Graph

1395 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
chaochaoweb3 7f892a8ee3 fix Ascend Qwen3.6 path separators (#511) 
Co-authored-by: 马千里 <ccw3@ccw3deMac-mini.local>
 2026-08-26 14:33:41 +08:00
Brill 51e5684d05 docs: 新增 MiniMax-M3 Lora 微调教程 (#514) 
* docs: add MiniMax-M3 BF16 LoRA tutorial

* docs: remove ServerChan integration from MiniMax tutorial
 2026-08-26 14:33:02 +08:00
牧小熊 7946e3f5c0 增加hy3模型的支持 (#515) 
* Revise table of contents and add supported models section

Updated the table of contents to include a new section for supported models and reorganized existing entries.

* Add files via upload

* Update deployment guide for Hy3-vLLM with Docker

* Fix formatting in supported models list
 2026-08-26 14:32:40 +08:00
HuskyLYL 85cc234317 docs: 新增 GLM-5.2 技术解读及 vLLM/SGLang 部署教程 (#516) 2026-08-26 14:32:09 +08:00
Yang Yu bfca4899f5 docs: add DeepSeek-V4-Flash SGLang deployment tutorial (#517) 
* docs: add DeepSeek-V4-Flash SGLang tutorial

* docs: add DeepSeek-V4-Flash SGLang screenshots

* docs: restore SGLang tutorial content

This section introduces the deployment of DeepSeek-V4-Flash using SGLang, providing OpenAI compatible interfaces. It includes two deployment methods: using SGLang's official Docker image on RTX PRO 6000 and deploying in a Python environment on NVIDIA H200.
 2026-08-26 14:29:46 +08:00
Yang Yu 2314e857fe docs: add DeepSeek-V4-Flash vLLM deployment tutorial (#518) 
* docs: add DeepSeek-V4-Flash vLLM tutorial

* docs: add DeepSeek-V4-Flash vLLM screenshots

* docs: restore vLLM tutorial content
 2026-08-26 14:24:18 +08:00
Octopus 4cc01ab0b1 docs: add MiniMax-M2.7 deployment guides (#521) 
Co-authored-by: octo-patch <266937838+octo-patch@users.noreply.github.com>
 2026-08-26 14:23:52 +08:00
不要葱姜蒜 baf3b69091 Update README.md 2026-07-30 09:58:21 +08:00
陈榆 710194b477 修改AMD的教程，并且增加AMD算力平台支持 (#519) 
* Gemma4教程

提交Gemma4教程

* 优化gemma4教程

* 修订一下

* docs: 将 AMD 专区切换为 ROCm 7（Gemma4 / Qwen3.5）

参考 hello-rocm 01-deploy 迁入部署教程，替换 models_amd 旧 Lemonade 内容，并更新入口页链接以引导深入学习。

Co-authored-by: Cursor <cursoragent@cursor.com>

* 增加致谢

* 增加算力支持

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-30 09:52:23 +08:00
XUAN 0932a89b0f docs: add DeepSeek-V4-Flash LoRA tutorial (#512) 2026-07-15 15:30:26 +08:00
KMnO4-zx 42c1bff433 dataset: update huanhuan samples 2026-06-17 13:54:34 +08:00
KMnO4-zx 1c5790c2f5 docs: add Qwen3.5 tutorials 2026-06-17 13:49:19 +08:00
KMnO4-zx 8b9fe2274f docs: add MiniCPM5 tutorials 2026-06-17 13:48:45 +08:00
Octopus 171b06a146 docs: 新增 MiniMax-M3 部署教程（vLLM/SGLang/Transformers） (#508) 
- 新增 MiniMax-M3 vLLM/SGLang/Transformers 三套部署教程
- 在 support_model.md、README.md、README_en.md 中加入 MiniMax-M3 入口
- 保留 MiniMax-M2.5、MiniMax-M2 已有教程

MiniMax-M3 相比 M2.5 升级为 512K 上下文、单次最大 128K 输出，并支持图片输入。
 2026-06-03 11:37:42 +08:00
Eleven Liu a7cd4ef135 add Qwen3.6 ascend docs (#505) 2026-04-24 21:50:47 +08:00
陈榆 0ae047b221 新增Gemma4教程 (#503) 
* Gemma4教程

提交Gemma4教程

* 优化gemma4教程
 2026-04-13 20:41:18 +08:00
Octopus 23dd98a696 docs: 新增 MiniMax-M2.5 部署教程（vLLM/SGLang/Transformers） (#500) 
* docs: add MiniMax-M2.5 vLLM deployment tutorial

* docs: add MiniMax-M2.5 SGLang deployment tutorial

* docs: add MiniMax-M2.5 Transformers deployment tutorial

* docs: add MiniMax-M2.5 to supported models list

* docs: add MiniMax-M2.5 to README model list

* docs: address review feedback on upgrade commands and HF-Mirror notes

- Add explicit `pip install -U vllm` upgrade command in vLLM troubleshooting
- Add explicit `pip install -U sglang` upgrade command in SGLang troubleshooting
- Add `pip show sglang` version check hint in SGLang environment setup
- Add `pip install -U transformers` upgrade command in Transformers troubleshooting
- Clarify that HF-Mirror is not needed when using modelscope to download models
  (applies to all three docs: vLLM, SGLang, Transformers)

---------

Co-authored-by: octo-patch <octo-patch@users.noreply.github.com>
 2026-03-27 17:14:57 +08:00
johnjim0816 8d75dd0104 ✨ feat:[Apple专区] 更新支持模型清单 2026-03-22 14:15:40 +08:00
johnjim0816 5500aab179 ✨ feat: 重构为模块化架构，新增 Gradio 交互平台 (#499) 2026-03-08 23:05:09 +08:00
John Law f804bdf941 Fix JSON key from 'rloe' to 'role' (#496) 
Updated JSON format for dialogue entries in readme.
 2026-02-25 00:03:51 +08:00
Xiaoyu Zhang a47df3df75 Update MiniMax-M2 blog with PR merge status (#497) 2026-02-25 00:02:50 +08:00
johnjim0816 99350d3fac ✨ feat: 增加MLX框架简介 (#492) 2026-02-10 11:34:48 +08:00
KMnO4-zx 4bd3c5f7c5 更新支持模型列表，添加 Kimi-K2.5 和 Step-3.5-Flash 的详细部署指南及相关贡献者信息 2026-02-09 21:48:23 +08:00
frtanxidian 4b41b1d181 Kimi2.5-SGLang-v1.0 (#485) 
* Kimi2.5-SGLang-v1.0

* kimi2.5sglangv2.0
 2026-02-09 21:19:29 +08:00
Yang Yu 6fe3cde820 New PR about GLM-4.7-Flash-Lora微调，增加swanlab详细说明 (#489) 2026-02-09 21:15:28 +08:00
frtanxidian 8a9d6616bc kimi2.5sglangv2.0 (#490) 2026-02-09 21:13:56 +08:00
sanshui 7912ab93cf Merge pull request #491 from sssanssss/GLM-4.7-Flash 
02-GLM-4.7-Flash SGLang 部署调用
 2026-02-09 21:12:26 +08:00
不要葱姜蒜 41429f9047 Merge pull request #488 from isaacahahah/master 
feat：新增step-3.5-flash-vllm部署教程
 2026-02-08 20:37:36 +08:00
kichi 6ba83fb9e4 ＂feat：新增step-3.5-flash-vllm部署教程＂ 2026-02-08 12:31:46 +00:00
kichi 40c1485a1d Merge branch 'datawhalechina:master' into master 2026-02-08 20:01:55 +08:00
不要葱姜蒜 d1788568d6 Merge pull request #487 from YangYu-NUAA/master 
GLM-4.7-Flash-Lora微调md及notebook文件
 2026-02-08 19:57:58 +08:00
Yang Yu 63b982dea7 Delete models/GLM-4.7-Flash/GLM-4.7-Flash.ipynb 2026-02-08 17:56:07 +08:00
Yang Yu 076604f9bd Update print statement from 'Hello' to 'Goodbye' 2026-02-08 17:54:59 +08:00
Yang Yu 5366858825 Add files via upload 2026-02-08 17:49:59 +08:00
Yang Yu 13d471a06e Add files via upload 2026-02-08 17:45:42 +08:00
Yang Yu 0ad1f3f6e2 Add files via upload 2026-02-08 17:45:01 +08:00
Yang Yu 80ab65de45 Add files via upload 2026-02-08 06:27:04 +08:00
不要葱姜蒜 8e3f7cda80 Merge pull request #484 from fanqiNO1/kimi-k2.5-tech-report 
kimi-k2.5 technical report (task 01)
 2026-02-07 21:12:55 +08:00
fanqiNO1 ca205d6ddc fix equations 2026-02-07 21:05:30 +08:00
fanqiNO1 4a81feb1e0 try to fix 2026-02-07 21:00:28 +08:00
fanqiNO1 76ba6aa470 try to fix 2026-02-07 20:59:30 +08:00
fanqiNO1 c4940cf2ff try to fix 2026-02-07 20:52:47 +08:00
fanqiNO1 4b2849dfe9 kimi-k2.5 01 task 2026-02-07 20:41:23 +08:00
不要葱姜蒜 80b6858c68 Merge pull request #481 from ilovexsir/master 
add glm-4.7-flash and kimi-2.5 vllm doc
 2026-02-07 17:46:01 +08:00
ilovescrapy caca8daa98 add glm-4.7-flash and kimi-2.5 vllm doc 
a

a
 2026-02-06 13:06:34 +08:00
不要葱姜蒜 b8dfc88a2f Merge pull request #483 from Fyuan0206/master 
修改Step-3.5-Flash-SGLang部分内容
 2026-02-06 12:58:15 +08:00
Fuyuan-bit 04475ed5ee 修改Step-3.5-Flash-SGLang部分内容 2026-02-06 12:44:03 +08:00
不要葱姜蒜 4222ceaafd Merge pull request #482 from Fyuan0206/master 
add Step-3.5-Flash-SGLang
 2026-02-06 11:50:49 +08:00
Fuyuan-bit a090aa2143 add Step-3.5-Flash-SGLang 2026-02-06 11:05:58 +08:00
kichi 756f3869cd Delete models/Step-3.5-Flash 2026-02-05 16:02:35 +08:00