meta-llama / llama-recipes
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.
☆14,965Updated this week
Related projects ⓘ
Alternatives and complementary repositories for llama-recipes
- A high-throughput and memory-efficient inference and serving engine for LLMs☆29,785Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆10,590Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆7,840Updated 6 months ago
- Inference code for CodeLlama models☆16,022Updated 2 months ago
- Inference code for Llama models☆56,320Updated 2 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆16,354Updated this week
- Large Language Model Text Generation Inference☆9,019Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,036Updated 4 months ago
- Finetune Llama 3.2, Mistral, Phi, Qwen & Gemma LLMs 2-5x faster with 80% less memory☆17,884Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,650Updated 3 months ago
- Go ahead and axolotl questions☆7,865Updated this week
- Python bindings for llama.cpp☆8,072Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,656Updated 3 weeks ago
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,258Updated 3 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆5,919Updated this week
- Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)☆33,946Updated this week
- A framework for few-shot evaluation of language models.☆6,904Updated this week
- Awesome-LLM: a curated list of Large Language Model☆18,684Updated this week
- DSPy: The framework for programming—not prompting—foundation models☆18,587Updated this week
- PyTorch native finetuning library☆4,267Updated this week
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆18,831Updated this week
- LlamaIndex is a data framework for your LLM applications☆36,584Updated this week
- Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"☆10,680Updated 2 months ago
- Train transformer language models with reinforcement learning.☆9,990Updated this week
- Tools for merging pretrained large language models.☆4,788Updated this week
- Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sag…☆13,670Updated this week
- Run any open-source LLMs, such as Llama, Gemma, as OpenAI compatible API endpoint in the cloud.☆10,006Updated this week
- Retrieval and Retrieval-augmented LLMs☆7,471Updated this week
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆12,326Updated last month
- Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)☆11,442Updated this week