Henri Johnson

Intermediate
@henri-edh

AirLLM. 33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

4

sage. Chat with any codebase with 2 commands

1

fintech-clone-react-native. Galaxies-Dev : React-Native Fintech Clone with Clerk Auth

1

connery. Connery - Plugin infrastructure for AI

1

st-chat-message. Streamlit chat message component

1

QuickAgent. Python

1

GROQ. Specification for GROQ - The Query Language for JSON

1

text-generation-inference. Large Language Model Text Generation Inference

1

OmniLMM. Large Multi-modal Models for Strong Performance and Efficient Deployment

1

RealtimeTTS. Converts text to speech in realtime

1

unsloth. 5X faster 60% less memory QLoRA finetuning

1

AssemblyAI-Applications. Here is a collection of cool applications that I've built with AssemblyAI

1

llama_index. LlamaIndex is a data framework for your LLM applications

1

conversational-chatbot-groq. Python

1

rag-chat-with-pdf. Simple Chainlit UI for running llms locally using Ollama and LangChain

1

mlarena. Algorithm-agnostic machine learning toolkit for strealined model training, diagnostics, and optimization.

1

AutoGroq. Python

1

raptor. The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

1

local_function_calling. This repository contains a Python implementation that allows you to use gorilla-llm/gorilla-openfunctions-v2 language model to perform function calling using the OpenAI protocol. It provides a way to extend the capabilities of the local model by enabling it to generate function arguments and execute functions based on the provided specifications.

1

magentic-litellm-tutorial. Jupyter Notebook

1

tortoise-tts-modal-api. Tortoise TTS pay-as-you-go API

1

Hermes-Function-Calling. Python

1

cappy. NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer

1

learnopencv. Learn OpenCV : C++ and Python Examples

1

moondream. tiny vision language model

1

chatd. Chat with your documents using local AI

1

mlc-llm. Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

1
27
Apply