Pinned Repositories
amulil
personal profile
asst1
Stanford CS149 -- Assignment 1
blog
boshi-sample-solution
FT-Data-Ranker-1B-No.8
FT-Data-Ranker 1B赛道 第 8 名方案
hg_dataset_scripts
some helpful scripts to deal with huggingface dataset
nanollm
a single python file to train and inference all kinds of llm.
Tao
the rl algos implementation inspired by cleanrl
vector_by_onnxmodel
accelerate generating vector by using onnx model
xtuner
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
amulil's Repositories
amulil/vector_by_onnxmodel
accelerate generating vector by using onnx model
amulil/hg_dataset_scripts
some helpful scripts to deal with huggingface dataset
amulil/Tao
the rl algos implementation inspired by cleanrl
amulil/FT-Data-Ranker-1B-No.8
FT-Data-Ranker 1B赛道 第 8 名方案
amulil/amulil
personal profile
amulil/asst1
Stanford CS149 -- Assignment 1
amulil/blog
amulil/boshi-sample-solution
amulil/hw0
amulil/hw1
amulil/Lux-AI-Season2-Solution
https://www.kaggle.com/competitions/lux-ai-season-2
amulil/nanollm
a single python file to train and inference all kinds of llm.
amulil/build-nanogpt
Video+code lecture on building nanoGPT from scratch
amulil/hw2
amulil/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
amulil/makefiletutorial
Learn make by example
amulil/minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
amulil/my_own_stable_diffusion
Setup My Own Stable Diffusion
amulil/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
amulil/nanoGPT-Tangpoetry
amulil/needle
necessary elements of deep learning
amulil/RLXF
A framework make the model like a human more and more.
amulil/SPIN
The official implementation of Self-Play Fine-Tuning (SPIN)
amulil/tools
some tools written by python
amulil/trl
Train transformer language models with reinforcement learning.
amulil/xtuner
A toolkit for efficiently fine-tuning LLM (InternLM, Llama, Baichuan, QWen, ChatGLM)