Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
TianyuFan0504 opened an issue on microsoft/Phi-3CookBook
The model requires too much GPU memory to process input prompt
When I use Phi-3.5-mini-instruct model, I found that the required memory for processing inputs is much more larger than other models/what is theoretically needed. Here is the code and the CUDA er...
TianyuFan0504 created a comment on an issue on HKUDS/LightRAG
Yes, you can switch you model to Openai()/Ollama/HF model.
TianyuFan0504 created a comment on an issue on HKUDS/LightRAG
> > Hi @shmily1012. We have understood your question. Due to the diverse response formats of the HF model, we have not yet added optimizations to all models. Your problem may arise from the followi...
TianyuFan0504 created a comment on an issue on HKUDS/LightRAG
能给出具体的报错信息吗？具体是在哪里报错的？ 我们没有测试过ChatGLM4-9B-Chat，但是根据我们测试其他1B 3B 4B 8B 模型的经验，这个量级的模型性能可能不足以支持复杂查询，提取到的实体种类也不够多，推荐使用14B以上的模型，最好是70B以上的。
TianyuFan0504 created a comment on an issue on HKUDS/LightRAG
可能是embedding_dim没设置对，查询时的emb_dim和你的本地存储的dim不一样
TianyuFan0504 created a comment on an issue on HKUDS/LightRAG
Hi @shmily1012. We have understood your question. Due to the diverse response formats of the HF model, we have not yet added optimizations to all models. Your problem may arise from the following...
TianyuFan0504 pushed 22 commits to main TianyuFan0504/LightRAG
- ollama test 10d1ac4
- update README.md 2b49f6e
- update requirements.txt 72200af
- update README.md cf869fc
- Merge pull request #25 from HKUDS/test Add Ollama models support ed7e051
- Update README.md 1e74af5
- Merge pull request #26 from HKUDS/test Update README.md 8c6e8dd
- Update README.md 7ab6999
- Add Discord channel link 0e0a037
- fix Ollama bugs a2f1654
- update Step_3.py and openai compatible script 70dbca1
- Merge pull request #39 from russellkim/main update Step_3.py and openai compatible script 19717e4
- Add a link to a LightRAG explanatory video 996c954
- Update README.md d04f70d
- Create lightrag_azure_openai_demo.py f576a28
- Update operate.py e7a7ff6
- Added support for Amazon Bedrock models 7050875
- Fixed retry strategy, message history and inference params; Cleaned up Bedrock example 75a91d9
- Add comment specifying jupyter req Add lines that can be uncommented if running in a jupyter notebook a7b43d2
- Merge pull request #49 from JGalego/feat/bedrock-support feat: Amazon Bedrock support ⛰️ b854ab4
- and 2 more ...
TianyuFan0504 created a comment on an issue on HKUDS/LightRAG
> and if I comment this line: `#nest_asyncio.apply()` > > I get this error: INFO:lightrag:Logger initialized for working directory: ./ DEBUG:lightrag:LightRAG init with param: working_dir = ./, ...
TianyuFan0504 created a branch on TianyuFan0504/LightRAG
ty_test - "LightRAG: Simple and Fast Retrieval-Augmented Generation"
TianyuFan0504 pushed 8 commits to main TianyuFan0504/LightRAG
- Add Star History 6389bae
- Add Star History c3a5c8a
- Merge branch 'main' of https://github.com/HKUDS/LightRAG into main 2b390ab
- Add Star history c8a7c4f
- Update README.md b651a2e
- Update README.md a1e3ca4
- Added OpenAI compatible options and examples b0ad877
- Merge pull request #16 from hunkimForks/main Added OpenAI compatible options and examples 3fabaf0