minyang's repositories
LLM_convert_receipt_image-to-json_or_xml
Finetune LLM to convert an invoice or receipt image to receipt XML or JSON object.
tinyllama_colorist
finetune tinyllama to generate color code
chatgpt_like_experience_locally
mimic chatgpt like experience locally using latest open source LLM models
Knowledge_Distillation_Training
employ knowledge distillation to compress their large deep models into lightweight versions (Teacher and Student Model)
llm-fine-tuning
fine-tuning large language model for specific business use case, problem or task
multi-nodes-slurm-cluster-docker
fully dockerized distributed multi-nodes slurm cluster - ubuntu 20.04
AutoAWQ
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
autogen
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
axolotl
Go ahead and axolotl questions
discord_bot
BIDARA is a GPT-4 chatbot that was instructed to help scientists and engineers understand, learn from, and emulate the strategies used by living things to create sustainable designs and technologies using the Biomimicry Institute's step-by-step design process.
gguf-chatbot-ui
An open source ChatGPT UI. (for GGUF models)
llama2.c
Inference Llama 2 in one file of pure C
LLaVA
Visual Instruction Tuning: Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
llm-awq
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
llm_fast_inference_from_HF_via_speculative_decoding
evaluate Speculative Decoding that promising 2-3X speedups of LLM inference by running two models in parallel.
Local-LLM-Comparison-Colab-UI
Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.
mctodo
a simple yet colorful CLI app to keep track of my todo list.
Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
MiniGPT-4
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
mojo
The Mojo Programming Language
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
piper
A fast, local neural text to speech system
RLHF_example
Reinforcement learning from human feedback (RLHF) Movie Reviews Example
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
single-node-slurm-cluster-docker
fully dockerized single-node slurm cluster with GPU support
slurm-job-samples
Slurm Job Samples encapsulate GPU resources
strictjson
A Strict JSON Framework for LLM Outputs
Video-LLaVA
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection