Alternatives and similar repositories for llama-cookbook

Users that are interested in llama-cookbook are comparing it to the libraries listed below

• haotian-liu / LLaVA
  [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
  ☆22,992Updated 11 months ago
• Lightning-AI / litgpt
  20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
  ☆12,445Updated this week
• huggingface / text-generation-inference
  Large Language Model Text Generation Inference
  ☆10,311Updated this week
• meta-llama / llama
  Inference code for Llama models
  ☆58,477Updated 5 months ago
• run-llama / llama_index
  LlamaIndex is the leading framework for building LLM-powered agents over your data.
  ☆42,937Updated this week
• axolotl-ai-cloud / axolotl
  Go ahead and axolotl questions
  ☆9,852Updated this week
• meta-llama / llama3
  The official Meta Llama 3 GitHub site
  ☆28,816Updated 5 months ago
• mistralai / mistral-inference
  Official inference library for Mistral models
  ☆10,338Updated 3 months ago
• jzhang38 / TinyLlama
  The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
  ☆8,631Updated last year
• vllm-project / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆51,794Updated this week
• pytorch / torchtune
  PyTorch native post-training library
  ☆5,306Updated this week
• artidoro / qlora
  QLoRA: Efficient Finetuning of Quantized LLMs
  ☆10,532Updated last year
• meta-llama / codellama
  Inference code for CodeLlama models
  ☆16,346Updated 10 months ago
• unslothai / unsloth
  Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
  ☆41,657Updated this week
• huggingface / peft
  🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
  ☆18,976Updated this week
• huggingface / trl
  Train transformer language models with reinforcement learning.
  ☆14,513Updated 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…
  ☆6,071Updated last week
• openai / tiktoken
  tiktoken is a fast BPE tokeniser for use with OpenAI's models.
  ☆15,055Updated 3 months ago
• karpathy / minbpe
  Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
  ☆9,731Updated last year
• Dao-AILab / flash-attention
  Fast and memory-efficient exact attention
  ☆18,252Updated this week
• openai / swarm
  Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
  ☆20,070Updated 4 months ago
• microsoft / LoRA
  Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
  ☆12,224Updated 6 months ago
• lm-sys / FastChat
  An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
  ☆38,825Updated last month
• arcee-ai / mergekit
  Tools for merging pretrained large language models.
  ☆5,965Updated 3 weeks ago
• nlpxucan / WizardLM
  LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
  ☆9,428Updated last month
• Hannibal046 / Awesome-LLM
  Awesome-LLM: a curated list of Large Language Model
  ☆24,182Updated this week
• letta-ai / letta
  Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.
  ☆17,157Updated last week
• abetlen / llama-cpp-python
  Python bindings for llama.cpp
  ☆9,313Updated this week
• meta-llama / llama-models
  Utilities intended for use with Llama models.
  ☆7,123Updated last month
• EleutherAI / lm-evaluation-harness
  A framework for few-shot evaluation of language models.
  ☆9,464Updated this week