Comments (6)
@abhi-0907 - thanks for clarifying - we will dig in over the next couple of days and figure out what is going wrong.
from llmware.
@abhi-0907 - please check out the file posted on Huggingface:
--repository: llmware/bonchon
--file: meditalk_4_Q_M_042124.gguf
Hope that this resolves the issue.... 😄
from llmware.
@abhi-0907 - thanks for sharing this. Your code looks spot-on, and would expect this to work. I have tested it locally, and can recreate the issue, e.g., I get the same error. It looks as if the gguf engine is not loading the model successfully. Just confirming that it is a Llama-7b base model, and was converted/quantized using a current build of llama-cpp? Any insights on the base model and the gguf build environment will definitely us to recreate the environment and figure out what is going wrong.
from llmware.
Yeah, It was Llama2 - 7b basemodel and it was quantized using a current build of llama-cpp on windows.
from llmware.
@abhi-0907 - FYI, I have tried recompiling our llama cpp libs, and am still having trouble getting the Meditalk2 Q4_K_M file to successfully load. Not seeing an issue with other llama GGUF models in testing. In experimenting, I re-quantized your original Pytorch meditalk model in Q4_K_M and it is working well (really nice finetuned output!) on both Mac and Windows CUDA. Perhaps there is some small, but significant, difference in the llama cpp build you used to quantize (?). I have posted the re-quantized version in a private HF repo - I didn't want to put in a public repo unless you said OK ... please confirm that you are OK, and I will post it in llmware/bonchon - or can upload it to you directly if you prefer ...
from llmware.
Thanks for resolving. You can post it on public repo.
from llmware.
Related Issues (20)
- JSON files not being parsed and are being rejected HOT 6
- Add class docstrings to module prompts HOT 1
- quickstart_rag_colab.ipynb
- streamlit and other UI examples HOT 1
- google colab examples and start up scripts HOT 2
- jupyter notebook - more examples and better support HOT 2
- Add Cohere Command R model
- GGUF models not utilising GPU on Windows HOT 2
- Can I use SLIM-Agents for german language?
- Error in Prompt.load(from_hf) : model_card (NoneType) is not iterable HOT 3
- move llmware base directory HOT 2
- Azure OpenAI Integration HOT 3
- Issue with the spelling of between HOT 1
- New HOT 1
- Prompt with sources example: create_new_library Error HOT 2
- Not able to load pretrained models HOT 3
- Don't able to create application in low-level machine HOT 3
- Running forever when running Llama-3 model locally HOT 2
- Library().delete_library does not delete the library HOT 6
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llmware.