Getting there slowly! Join us to build the best Hindi/Hinglish Open LLM collaboratively. If you want to collaborate, join hinglish-training channel on Hugging Face Discord This model was finetuned on hindi/hinglish data using mistral as base model using AutoTrain, without
OPEN SOURCE
-
Customizing LangChain with Neo4j for Advanced RAG Systems
By
–
Customized LangChain @neo4j Integration If you want to build advanced RAG, you probably need to know how to customize any off-the-shelf guide to your use case @tb_tomaz dives deep on how to do this with Graph DBs like Neo4j Blog: https://
github.com/langchain-ai/l
angchain/pull/15084
… -
RAG Inference with Local Models on CPUs
By
–
RAG on CPUs (with Intel Developer Cloud) Retrieval Augmented Generation is a great way to combine YOUR data with LLMs… which is why it's so nice to be able to do this with local models This great goes over how to do that (with CPUs no less!) Blog: https://
towardsdatascience.com/retrieval-augm
ented-generation-rag-inference-engines-with-langchain-on-cpus-d5d55f398502
… -
AutoTrain Now Supports Chat Templates in UI and CLI
By
–
Now you can apply chat template directly in the AutoTrain UI or CLI and train on datasets like H4's no_robots without any extra effort. Just `pip install autotrain-advanced` to run it locally or deploy on huggingface spaces.
-
Hugging Face Fellows Winter Edition: Outstanding Open-Source ML Contributions
By
–
Hugging Face Fellows is a network of exceptional people who contribute to open-source machine learning Excited to present you the amazing work of our Fellows, Winter edition https://
huggingface2.notion.site/Hugging-Face-F
ellows-Highlights-Winter-Edition-b26c2c7d3f9143ec88d98ec43b98af29?pvs=4
…
The repositories can be found here https://
huggingface.co/collections/hu
gging-fellows/fellows-highlights-winter-23-dec-658c14b6eaba17684e657014
… -
Cerebras advances open source LLM development with custom model recipes
By
–
Cerebras led the way in open source AI development in 2024 – releasing complete recipes for model weights, training code, and data. Our ML team is constantly inventing new techniques to train LLMs for different languages and modalities – contact us to build your own custom model!
-
RAG Chatbot Tutorial: LLaMA-2, Qdrant, LangChain, Streamlit
By
–
RAG Tutorial from Oracle Generative AI Chatbot using LLaMA-2, @qdrant_engine
, RAG, LangChain & @streamlit Really detailed blog post walking through ingestion, setting up a chain, and making it look great in the UI Blog: https://
blogs.oracle.com/ai-and-datasci
ence/post/ai-chatbot-llama2-qdrant-rag-langchain-streamlit
… -
Discussion on the utility of the MLX machine learning framework
By
–
Yes j’ai pas relayé mlx parce que je l’ai pas testé, et je préfère tester avant d’en parler mais je l’ai vu passé. C’est comment ? C’est utile ?