Pinned Loading

1. Llama-2-7B-Chat-PEFT Llama-2-7B-Chat-PEFT Public

   PEFT is a wonderful tool that enables training a very large model in a low resource environment. Quantization and PEFT will enable widespread adoption of LLM.

   Jupyter Notebook 2 1

2. Embedding-Quantization Embedding-Quantization Public

   To make LLM faster we need faster retrieval system. Here comes Embedding Quantization. Embedding quantization is great technique to save cost on Vector DB, significantly faster retrieval while pres…

   Jupyter Notebook 1

3. LlamaIndex-Agent LlamaIndex-Agent Public

   A RAG system is just the beginning of harnessing the power of LLM. The next step is creating an intelligent Agent. In Agentic RAG the Agent makes use of available tools, strategies and LLM to gener…

   Jupyter Notebook 1

4. Phi3-No-GPU-No-Worry Phi3-No-GPU-No-Worry Public

   GPU constrained! No More. Microsoft released Phi3 specially designed for memory/compute constrained environments. The model support ONXX CPU runtime which offers amazing inference speed even on mob…

   Jupyter Notebook 1

5. Fine-tuning-BART Fine-tuning-BART Public

   Fine Tuning is a cost-efficient way of preparing a model for specialized tasks. Fine-tuning reduces required training time as well as training datasets. We have open-source pre-trained models. Henc…

   Jupyter Notebook

6. LlamaIndex-Agent-with-Reasoning-Loop LlamaIndex-Agent-with-Reasoning-Loop Public

   Simple agents are good for 1-to-1 retrieval system. For more complex task we need multi steps reasoning loop. In a reasoning loop the agent can break down a complex task into subtasks and solve the…

   Jupyter Notebook