Alternatives and similar repositories for trl

Users that are interested in trl are comparing it to the libraries listed below

• huggingface / peft
  🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
  ☆19,498Updated this week
• Dao-AILab / flash-attention
  Fast and memory-efficient exact attention
  ☆19,275Updated last week
• EleutherAI / lm-evaluation-harness
  A framework for few-shot evaluation of language models.
  ☆10,038Updated this week
• bitsandbytes-foundation / bitsandbytes
  Accessible large language models via k-bit quantization for PyTorch.
  ☆7,533Updated this week
• OpenRLHF / OpenRLHF
  An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…
  ☆7,846Updated this week
• huggingface / accelerate
  🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…
  ☆9,086Updated last week
• CarperAI / trlx
  A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
  ☆4,707Updated last year
• volcengine / verl
  verl: Volcano Engine Reinforcement Learning for LLMs
  ☆13,053Updated this week
• pytorch / torchtune
  PyTorch native post-training library
  ☆5,458Updated this week
• eric-mitchell / direct-preference-optimization
  Reference implementation for DPO (Direct Preference Optimization)
  ☆2,724Updated last year
• huggingface / alignment-handbook
  Robust recipes to align language models with human and AI preferences
  ☆5,343Updated last month
• artidoro / qlora
  QLoRA: Efficient Finetuning of Quantized LLMs
  ☆10,648Updated last year
• microsoft / LoRA
  Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
  ☆12,627Updated 8 months ago
• sgl-project / sglang
  SGLang is a fast serving framework for large language models and vision language models.
  ☆17,656Updated this week
• NVIDIA / Megatron-LM
  Ongoing research training transformer models at scale
  ☆13,458Updated this week
• deepspeedai / DeepSpeedExamples
  Example models using DeepSpeed
  ☆6,656Updated 2 weeks ago
• opendilab / awesome-RLHF
  A curated list of reinforcement learning with human feedback resources (continually updated)
  ☆4,127Updated last month
• yizhongw / self-instruct
  Aligning pretrained language models with instruction data generated by themselves.
  ☆4,465Updated 2 years ago
• arcee-ai / mergekit
  Tools for merging pretrained large language models.
  ☆6,258Updated 3 weeks ago
• allenai / RL4LMs
  A modular RL library to fine-tune language models to human preferences
  ☆2,344Updated last year
• huggingface / text-generation-inference
  Large Language Model Text Generation Inference
  ☆10,477Updated this week
• OpenGVLab / LLaMA-Adapter
  [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
  ☆5,893Updated last year
• microsoft / LMOps
  General technology for enabling AI capabilities w/ LLMs and MLLMs
  ☆4,101Updated 2 months ago
• FlagOpen / FlagEmbedding
  Retrieval and Retrieval-augmented LLMs
  ☆10,452Updated last week
• Lightning-AI / lit-llama
  Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…
  ☆6,079Updated 2 months ago
• mit-han-lab / streaming-llm
  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks
  ☆7,030Updated last year
• openai / transformer-debugger
  ☆4,089Updated last year
• allenai / open-instruct
  AllenAI's post-training codebase
  ☆3,166Updated this week
• microsoft / unilm
  Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
  ☆21,702Updated 2 months ago
• axolotl-ai-cloud / axolotl
  Go ahead and axolotl questions
  ☆10,324Updated this week