23 results found Sort:

modelscope
ms-swift modelscope
412
4.7k
apache-2.0
23
Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL...
dpo llm sft lora peft vllm agent liger llama qwen2 deploy llama3 lora-ga emu3-gen internvl qwen2-vl minicpm-v modelscope multimodal pre-training
Created 2023-08-01
1,273 commits to main branch, last one 6 hours ago
shibing624
MedicalGPT shibing624
513
3.4k
apache-2.0
38
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
dpo gpt llm llama chatgpt medical medicalgpt
Created 2023-06-02
540 commits to main branch, last one 4 days ago
ContextualAI
HALOs ContextualAI
46
768
apache-2.0
8
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
dpo kto ppo rlhf halos alignment
Created 2023-12-03
212 commits to main branch, last one 9 days ago
jianzhnie
LLamaTuner jianzhnie
63
583
apache-2.0
9
Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.
dpo ppo qwen rlhf llama qlora llama3 chatgpt mixtral
Created 2023-05-25
537 commits to main branch, last one 5 months ago
ukairia777
tensorflow-nlp-tutorial ukairia777
270
534
unknown
5
tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning NLP 저장소입니다.
dpo llm nlp sft bert lora llama trainer bert-ner tensorflow huggingface nlp-tutorial transformers keras-tutorial question-answering named-entity-recognition natural-language-processing
Created 2021-12-30
259 commits to main branch, last one 3 months ago
dvlab-research
Step-DPO dvlab-research
11
310
unknown
2
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
dpo llm math reasoning
Created 2024-06-24
19 commits to main branch, last one 5 months ago
TUDB-Labs
mLoRA TUDB-Labs
54
284
apache-2.0
3
An Efficient "Factory" to Build Multiple LoRA Adapters
dpo gpu llm lora peft rlhf llama mlora llama2 chatglm baichuan finetune
Created 2023-08-24
306 commits to main branch, last one 12 days ago
PKU-Alignment
align-anything PKU-Alignment
55
274
apache-2.0
9
Align Anything: Training All-modality Model with Feedback
dpo rlhf chameleon multimodal large-language-models vision-language-model
Created 2024-07-14
66 commits to main branch, last one 2 days ago
armbues
SiLLM armbues
23
234
mit
8
SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.
dpo llm mlx lora llm-training apple-silicon llm-inference large-language-models
Created 2024-01-11
485 commits to main branch, last one 2 days ago
RockeyCoss
SPO RockeyCoss
4
164
mit
5
Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
dpo sdxl text-to-image diffusion-models text-to-image-generation
Created 2024-05-26
1 commits to main branch, last one 4 days ago
argilla-io
notus argilla-io
14
163
mit
6
Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach
dpo trl zephyr fine-tuning lm-alignment preference-data alignment-handbook
Created 2023-11-16
52 commits to main branch, last one about a year ago
YangLing0818
IterComp YangLing0818
9
152
mit
3
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
dpo rlhf text-to-image reward-modeling
Created 2024-10-09
10 commits to main branch, last one about a month ago
TideDra
VL-RLHF TideDra
7
140
apache-2.0
4
A RLHF Infrastructure for Vision-Language Models
dpo llm lmm vlm mllm rlhf
Created 2023-12-27
7 commits to main branch, last one about a month ago
anilca
NetTrader.Indicator anilca
52
140
unknown
16
Technical anaysis library for .NET
adl adx atr cci cmf cmo dpo ema obv pvt roc rsi sar dema macd trix envelope momentum ichimoku-cloud bollinger-bands
Created 2016-06-30
64 commits to master branch, last one 3 years ago
NiuTrans
Vision-LLM-Alignment NiuTrans
6
90
unknown
3
This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.
dpo llm ppo sft mllm rlhf llava reward vision alignment multi-model llama3-vision
Created 2024-06-29
40 commits to master branch, last one 2 months ago
sail-sg
oat sail-sg
6
72
apache-2.0
5
🌾 OAT: Online AlignmenT for LLMs
dpo llm rlhf alignment llm-aligment distributed-rl dueling-bandits llm-exploration online-alignment thompson-sampling distributed-training
Created 2024-10-15
22 commits to main branch, last one 13 hours ago
martin-wey
CodeUltraFeedback martin-wey
5
67
mit
3
CodeUltraFeedback: aligning large language models to coding preferences
dpo alignment codal-bench llm-as-a-judge code-generation codeultrafeedback large-language-models
Created 2024-01-25
51 commits to main branch, last one 5 months ago
YangLing0818
SuperCorrect-llm YangLing0818
1
41
unknown
3
SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights
dpo llm reflection llm-reasoning
Created 2024-10-11
9 commits to main branch, last one 2 months ago
junkangwu
beta-DPO junkangwu
0
36
unknown
2
[NeurIPS 2024] Official code of $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
dpo rlhf alignment preference-alignment
Created 2024-05-22
9 commits to main branch, last one about a month ago
TianduoWang
DPO-ST TianduoWang
5
30
mit
3
[ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
dpo chain-of-thought math-word-problem
Created 2024-06-04
9 commits to main branch, last one 4 months ago
sugarandgugu
Simple-Trl-Training sugarandgugu
1
29
unknown
1
基于DPO算法微调语言大模型，简单好上手。
dpo llm trl rlhf simple
Created 2024-03-27
16 commits to master branch, last one 5 months ago
RobinSmits
Dutch-LLMs RobinSmits
0
28
mit
3
Various training, inference and validation code and results related to Open LLM's that were pretrained (full or partially) on the Dutch language.
dpo trl peft qwen2 alpaca polylm pytorch open-llama transformers large-language-models
Created 2023-07-02
29 commits to main branch, last one 8 months ago
dannylee1020
openpo dannylee1020
0
25
apache-2.0
3
Framework for building synthetic datasets with AI feedback
ai dpo llm rlhf rlaif python evaluation finetuning ai-feedback huggingface llm-evaluation synthetic-data synthetic-data-generation
Created 2024-10-28
231 commits to master branch, last one 18 hours ago