Pinned Repositories
Adversarial-Large-Character-Set-CAPTCHA-Generation
alpaca-lora
Instruct-tune LLaMA on consumer hardware
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
caselab
demix
DEMix Layers for Modular Language Modeling
diffusion-lora
easy-llm-finetuner
Easy Environment Configuration for LLM Model Finetuning
falcontune
Tune any FALCON in 4-bit
lm-evaluation-harness
A framework for few-shot evaluation of language models.
MedVicuna
s1ghhh's Repositories
s1ghhh/MedVicuna
s1ghhh/lm-evaluation-harness
A framework for few-shot evaluation of language models.
s1ghhh/Adversarial-Large-Character-Set-CAPTCHA-Generation
s1ghhh/alpaca-lora
Instruct-tune LLaMA on consumer hardware
s1ghhh/bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
s1ghhh/caselab
s1ghhh/demix
DEMix Layers for Modular Language Modeling
s1ghhh/diffusion-lora
s1ghhh/easy-llm-finetuner
Easy Environment Configuration for LLM Model Finetuning
s1ghhh/falcontune
Tune any FALCON in 4-bit
s1ghhh/FasterTransformer
Transformer related optimization, including BERT, GPT
s1ghhh/LLM-Pruner
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.
s1ghhh/m-bbox
s1ghhh/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
s1ghhh/s1ghhh.github.io
Github Pages
s1ghhh/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
s1ghhh/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
s1ghhh/LLM-Drop
The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".
s1ghhh/mergekit
Tools for merging pretrained large language models.
s1ghhh/representation-engineering
Representation Engineering: A Top-Down Approach to AI Transparency
s1ghhh/SVD-LLM
Official Code for "SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression"
s1ghhh/TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
s1ghhh/wanda
A simple and effective LLM pruning approach.