minyang-chen

chain-of-thoughts-agent

Chain of Thoughts is a MRKL system - a modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning built on top of LLMs.

chatgpt_like_experience_locally

mimic chatgpt like experience locally using latest open source LLM models

distributed_train_finetune

Experiement with LLM Distributed Train and Fine-Tuning

h20_llm

Fine-tuning an LLM model with H2O LLM Studio to generate Cypher statements Avoid depending on external and ever changing APIs for your knowledge graph based chatbot

intuitive_thinker

To enhance the reasoning capabilities of smaller-sized language models, employ a system of thinking that incorporates mental models, structured Chain-of-Thought processes, and thoughtful reflection before responding to user queries.

Knowledge_Distillation_Training

employ knowledge distillation to compress their large deep models into lightweight versions (Teacher and Student Model)

LLM_convert_receipt_image-to-json_or_xml

Finetune LLM to convert an invoice or receipt image to receipt XML or JSON object.

single-node-slurm-cluster-docker

fully dockerized single-node slurm cluster with GPU support

tinyllama_colorist

finetune tinyllama to generate color code

minyang-chen/LLM_convert_receipt_image-to-json_or_xml

Finetune LLM to convert an invoice or receipt image to receipt XML or JSON object.

minyang-chen/tinyllama_colorist

finetune tinyllama to generate color code

minyang-chen/intuitive_thinker

To enhance the reasoning capabilities of smaller-sized language models, employ a system of thinking that incorporates mental models, structured Chain-of-Thought processes, and thoughtful reflection before responding to user queries.

minyang-chen/chatgpt_like_experience_locally

mimic chatgpt like experience locally using latest open source LLM models

minyang-chen/Knowledge_Distillation_Training

employ knowledge distillation to compress their large deep models into lightweight versions (Teacher and Student Model)

minyang-chen/single-node-slurm-cluster-docker

fully dockerized single-node slurm cluster with GPU support

minyang-chen/distributed_train_finetune

Experiement with LLM Distributed Train and Fine-Tuning

minyang-chen/multi-nodes-slurm-cluster-docker

fully dockerized distributed multi-nodes slurm cluster - ubuntu 20.04

minyang-chen/slurm-job-samples

Slurm Job Samples encapsulate GPU resources

minyang-chen/AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.

minyang-chen/autogen

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

minyang-chen/axolotl

Go ahead and axolotl questions

minyang-chen/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.

minyang-chen/gguf-chatbot-ui

An open source ChatGPT UI. (for GGUF models)

minyang-chen/llama2.c

Inference Llama 2 in one file of pure C

minyang-chen/LLaVA

Visual Instruction Tuning: Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.

minyang-chen/llm-awq

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

minyang-chen/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.

minyang-chen/Local-LLM-Comparison-Colab-UI

Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.

minyang-chen/mctodo

a simple yet colorful CLI app to keep track of my todo list.

minyang-chen/Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

minyang-chen/minyang-chen

minyang-chen/mojo

The Mojo Programming Language

minyang-chen/nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

minyang-chen/paligemma-receipt-json-v2

demo usage of paligemma extraction of receipt image to json object

minyang-chen/piper

A fast, local neural text to speech system

minyang-chen/RLHF_example

Reinforcement learning from human feedback (RLHF) Movie Reviews Example

minyang-chen/silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

minyang-chen/strictjson

A Strict JSON Framework for LLM Outputs

minyang-chen/Video-LLaVA

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection