xhedit / quantkitLinks
cli tool to quantize gguf, gptq, awq, hqq and exl2 models
☆76Updated 10 months ago
Alternatives and similar repositories for quantkit
Users that are interested in quantkit are comparing it to the libraries listed below
Sorting:
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆43Updated this week
- A python package for developing AI applications with local LLMs.☆151Updated 9 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆178Updated last year
- entropix style sampling + GUI☆27Updated last year
- A pipeline parallel training script for LLMs.☆159Updated 6 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆95Updated 5 months ago
- Easily view and modify JSON datasets for large language models☆83Updated 5 months ago
- Gradio based tool to run opensource LLM models directly from Huggingface☆96Updated last year
- ☆116Updated 10 months ago
- ☆162Updated 2 months ago
- Create text chunks which end at natural stopping points without using a tokenizer☆25Updated 7 months ago
- ☆67Updated last year
- automatically quant GGUF models☆214Updated last week
- An unsupervised model merging algorithm for Transformers-based language models.☆106Updated last year
- Distributed Inference for mlx LLm☆97Updated last year
- 5X faster 60% less memory QLoRA finetuning☆21Updated last year
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆52Updated 8 months ago
- Experimental LLM Inference UX to aid in creative writing☆123Updated 10 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆80Updated last year
- run ollama & gguf easily with a single command☆52Updated last year
- Very basic framework for composable parameterized large language model (Q)LoRA / (Q)Dora fine-tuning using mlx, mlx_lm, and OgbujiPT.☆42Updated 4 months ago
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.☆97Updated 4 months ago
- Let's create synthetic textbooks together :)☆75Updated last year
- All the world is a play, we are but actors in it.☆50Updated 3 months ago
- Forces DeepSeek R1 models to engage in extended reasoning by intercepting early termination tokens.☆19Updated 8 months ago
- The hearth of The Pulsar App, fast, secure and shared inference with modern UI☆58Updated 10 months ago
- ☆24Updated 9 months ago
- 1.58-bit LLaMa model☆83Updated last year
- After my server ui improvements were successfully merged, consider this repo a playground for experimenting, tinkering and hacking around…☆53Updated last year
- Tcurtsni: Reverse Instruction Chat, ever wonder what your LLM wants to ask you?☆23Updated last year