arcee-ai / mergekitLinks
Tools for merging pretrained large language models.
☆5,937Updated 2 weeks ago
Alternatives and similar repositories for mergekit
Users that are interested in mergekit are comparing it to the libraries listed below
Sorting:
- PyTorch native post-training library☆5,296Updated this week
- A framework for few-shot evaluation of language models.☆9,423Updated this week
- Go ahead and axolotl questions☆9,810Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,614Updated this week
- Robust recipes to align language models with human and AI preferences☆5,241Updated 2 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,113Updated 3 weeks ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,000Updated 2 months ago
- AllenAI's post-training codebase☆3,033Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,788Updated last week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,879Updated 2 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,200Updated last month
- Accessible large language models via k-bit quantization for PyTorch.☆7,192Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,921Updated 11 months ago
- ☆4,084Updated last year
- Modeling, training, eval, and inference code for OLMo☆5,739Updated this week
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,218Updated last month
- SGLang is a fast serving framework for large language models and vision language models.☆15,567Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,599Updated last year
- An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)☆4,628Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,551Updated last year
- Train transformer language models with reinforcement learning.☆14,435Updated this week
- Large Language Model Text Generation Inference☆10,265Updated last week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,165Updated last month
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,518Updated last year
- Minimalistic large language model 3D-parallelism training☆1,956Updated last week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,434Updated last week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,348Updated last week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,838Updated last year
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆12,380Updated this week
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,781Updated 6 months ago