Alternatives and similar repositories for trl

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

• EleutherAI / lm-evaluation-harness
  A framework for few-shot evaluation of language models.
  ☆9,802Updated last week
• huggingface / peft
  🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
  ☆19,298Updated this week
• Dao-AILab / flash-attention
  Fast and memory-efficient exact attention
  ☆18,897Updated 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…
  ☆7,653Updated this week
• bitsandbytes-foundation / bitsandbytes
  Accessible large language models via k-bit quantization for PyTorch.
  ☆7,471Updated 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…
  ☆9,032Updated this week
• artidoro / qlora
  QLoRA: Efficient Finetuning of Quantized LLMs
  ☆10,617Updated last year
• CarperAI / trlx
  A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
  ☆4,694Updated last year
• arcee-ai / mergekit
  Tools for merging pretrained large language models.
  ☆6,170Updated 2 weeks ago
• pytorch / torchtune
  PyTorch native post-training library
  ☆5,418Updated this week
• volcengine / verl
  verl: Volcano Engine Reinforcement Learning for LLMs
  ☆12,341Updated this week
• NVIDIA / Megatron-LM
  Ongoing research training transformer models at scale
  ☆13,219Updated this week
• huggingface / alignment-handbook
  Robust recipes to align language models with human and AI preferences
  ☆5,318Updated 3 weeks ago
• sgl-project / sglang
  SGLang is a fast serving framework for large language models and vision language models.
  ☆16,953Updated this week
• eric-mitchell / direct-preference-optimization
  Reference implementation for DPO (Direct Preference Optimization)
  ☆2,700Updated last year
• vllm-project / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆55,160Updated this week
• yizhongw / self-instruct
  Aligning pretrained language models with instruction data generated by themselves.
  ☆4,453Updated 2 years ago
• microsoft / LoRA
  Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
  ☆12,544Updated 8 months ago
• allenai / open-instruct
  AllenAI's post-training codebase
  ☆3,105Updated last week
• huggingface / text-generation-inference
  Large Language Model Text Generation Inference
  ☆10,424Updated this 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…
  ☆6,083Updated last month
• axolotl-ai-cloud / axolotl
  Go ahead and axolotl questions
  ☆10,205Updated this week
• Lightning-AI / litgpt
  20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
  ☆12,620Updated last week
• microsoft / LMOps
  General technology for enabling AI capabilities w/ LLMs and MLLMs
  ☆4,087Updated last month
• NVIDIA / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆6,270Updated last year
• opendilab / awesome-RLHF
  A curated list of reinforcement learning with human feedback resources (continually updated)
  ☆4,095Updated last month
• FlagOpen / FlagEmbedding
  Retrieval and Retrieval-augmented LLMs
  ☆10,332Updated last month
• jzhang38 / TinyLlama
  The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
  ☆8,700Updated last year
• allenai / RL4LMs
  A modular RL library to fine-tune language models to human preferences
  ☆2,338Updated last year
• mit-han-lab / streaming-llm
  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks
  ☆7,009Updated last year