arcee-ai / mergekitLinks
Tools for merging pretrained large language models.
☆6,718Updated last week
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☆5,660Updated this week
- Go ahead and axolotl questions☆11,171Updated this week
- Robust recipes to align language models with human and AI preferences☆5,481Updated 4 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,074Updated last week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,028Updated 9 months ago
- A framework for few-shot evaluation of language models.☆11,298Updated last week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,312Updated 8 months ago
- AllenAI's post-training codebase☆3,551Updated last week
- Accessible large language models via k-bit quantization for PyTorch.☆7,931Updated last week
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,431Updated last month
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,180Updated 5 months ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,639Updated last year
- Train transformer language models with reinforcement learning.☆17,206Updated this week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,705Updated 8 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,291Updated 2 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,431Updated 6 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,560Updated last week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,859Updated last week
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,556Updated 3 weeks ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,699Updated last year
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆2,159Updated last year
- Large Language Model Text Generation Inference☆10,749Updated 3 weeks ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,896Updated 2 years ago
- Minimalistic large language model 3D-parallelism training☆2,529Updated last month
- Enforce the output format (JSON Schema, Regex etc) of a language model☆1,985Updated 5 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,654Updated last year
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,177Updated last year
- Modeling, training, eval, and inference code for OLMo☆6,299Updated 2 months ago
- TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.☆3,331Updated 6 months ago
- [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which ach…☆5,812Updated 3 months ago