There are 0 repository under sft topic.
ms-swift: Use PEFT or Full-parameter to finetune 300+ LLMs or 50+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3, Llava-Video, Internvl2, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)
chatglm 6b finetuning and alpaca finetuning
聚宝盆(Cornucopia): 中文金融系列开源可商用大模型,并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)
tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning NLP 저장소입니다.
Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"
Ethereum Semi Fungible Standard (ERC-1155)
Elven Tools CLI - command line tool for launching NFTs collections on the MultiversX blockchain (Plus other tools).
This repo contains the codes for supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) designed for vision LLMs.
This repo contains some extensions of deepspeed-chat for fine-tuning LLMs (SFT+RLHF).
LDPC MATLAB simulation using BPSK + AWGN modulation decoded using Sum Product and Min Sum Algorithm
Train expert conversational role-play LLMs with synthetic data
Elven Tools SFT Minter Smart Contract - launching SFTs collections on the MultiversX blockchain
Testing the security of sanitizers by learning symbolic finite transducers
MultiversX library for interacting with the MultiversX blockchain's Non-fungible tokens and Semi-fungible tokens.
It's a GPT2 finetune project based on peft and transformers. Although can provide quite a imporvement, however, the illusion and inteligent is terrible.
Supervised Fine tuning using TRL library
Finetune Mistral 7b v1.0 on custom dataset
Scripts to keep up with latest scaleft packages to build them for AUR
Upload folders faster via SFTP by temporarily zipping on the client and unzipping on the host.
100000-Instruction-Following-Evaluation-SFT-for-Chinese-LLM-Text-Data
Advancing Prompt Evolution through Hybridization