RichardKelley / hflm
A simple library for working with Hugging Face models.
☆14Updated last month
Alternatives and similar repositories for hflm:
Users that are interested in hflm are comparing it to the libraries listed below
- implementation of https://arxiv.org/pdf/2312.09299☆20Updated 7 months ago
- entropix style sampling + GUI☆25Updated 3 months ago
- Local LLM inference & management server with built-in OpenAI API☆31Updated 10 months ago
- An AI character interaction system with emotional modeling and advanced memory management☆15Updated 3 months ago
- ☆22Updated 8 months ago
- A clone of OpenAI's Tokenizer page for HuggingFace Models☆44Updated last year
- Fast approximate inference on a single GPU with sparsity aware offloading☆38Updated last year
- Latent Large Language Models☆17Updated 5 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆46Updated last month
- Very minimal (and stateless) agent framework☆41Updated last month
- One Line To Build Zero-Data Classifiers in Minutes☆36Updated 4 months ago
- Modified Beam Search with periodical restart☆12Updated 5 months ago
- Simple LLM inference server☆20Updated 8 months ago
- A sleek, customizable interface for managing LLMs with responsive design and easy agent personalization.☆15Updated 5 months ago
- ☆31Updated last year
- a lightweight, open-source blueprint for building powerful and scalable LLM chat applications☆30Updated 8 months ago
- Simple, Fast, Parallel Huggingface GGML model downloader written in python☆24Updated last year
- Experimental sampler to make LLMs more creative☆30Updated last year
- ☆49Updated 11 months ago
- Nexusflow function call, tool use, and agent benchmarks.☆19Updated 2 months ago
- ☆48Updated 3 months ago
- Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and min…☆25Updated 3 months ago
- Karpathy's llama2.c transpiled to MLX for Apple Silicon☆15Updated last year
- A new way to generate large quantities of high quality synthetic data (on par with GPT-4), with better controllability, at a fraction of …☆22Updated 4 months ago
- Training hybrid models for dummies.☆20Updated last month
- An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO☆28Updated last week
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 11 months ago