Alternatives and similar repositories for mergekit

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

• axolotl-ai-cloud / axolotl
  Go ahead and axolotl questions
  ☆10,405Updated this week
• huggingface / alignment-handbook
  Robust recipes to align language models with human and AI preferences
  ☆5,356Updated last week
• argilla-io / distilabel
  Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…
  ☆2,878Updated last week
• pytorch / torchtune
  PyTorch native post-training library
  ☆5,484Updated this week
• allenai / open-instruct
  AllenAI's post-training codebase
  ☆3,180Updated this week
• EleutherAI / lm-evaluation-harness
  A framework for few-shot evaluation of language models.
  ☆10,091Updated this week
• AutoGPTQ / AutoGPTQ
  An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
  ☆4,942Updated 5 months ago
• predibase / lorax
  Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
  ☆3,417Updated 3 months ago
• huggingface / datatrove
  Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
  ☆2,616Updated 3 weeks ago
• stanfordnlp / pyreft
  Stanford NLP Python library for Representation Finetuning (ReFT)
  ☆1,512Updated 7 months ago
• casper-hansen / AutoAWQ
  AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
  ☆2,247Updated 4 months ago
• huggingface / text-generation-inference
  Large Language Model Text Generation Inference
  ☆10,491Updated last week
• S-LoRA / S-LoRA
  S-LoRA: Serving Thousands of Concurrent LoRA Adapters
  ☆1,852Updated last year
• mit-han-lab / streaming-llm
  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks
  ☆7,038Updated last year
• allenai / OLMo
  Modeling, training, eval, and inference code for OLMo
  ☆5,985Updated last week
• FasterDecoding / Medusa
  Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
  ☆2,618Updated last year
• gkamradt / LLMTest_NeedleInAHaystack
  Doing simple retrieval from LLM models at various context lengths to measure accuracy
  ☆2,020Updated last year
• huggingface / trl
  Train transformer language models with reinforcement learning.
  ☆15,520Updated this week
• bitsandbytes-foundation / bitsandbytes
  Accessible large language models via k-bit quantization for PyTorch.
  ☆7,584Updated this week
• turboderp-org / exllamav2
  A fast inference library for running LLMs locally on modern consumer-class GPUs
  ☆4,309Updated last month
• huggingface / lighteval
  Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
  ☆1,890Updated this week
• mistralai / mistral-finetune
  ☆3,016Updated last year
• noamgat / lm-format-enforcer
  Enforce the output format (JSON Schema, Regex etc) of a language model
  ☆1,918Updated 3 weeks ago
• jquesnelle / yarn
  YaRN: Efficient Context Window Extension of Large Language Models
  ☆1,606Updated last year
• EleutherAI / pythia
  The hub for EleutherAI's work on interpretability and learning dynamics
  ☆2,614Updated 3 months ago
• jiaweizzhao / GaLore
  GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
  ☆1,603Updated 10 months ago
• microsoft / LLMLingua
  [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…
  ☆5,407Updated 6 months ago
• huggingface / nanotron
  Minimalistic large language model 3D-parallelism training
  ☆2,191Updated last week
• artidoro / qlora
  QLoRA: Efficient Finetuning of Quantized LLMs
  ☆10,656Updated last year
• McGill-NLP / llm2vec
  Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
  ☆1,585Updated 7 months ago