MDK8888 / GPTFastLinks
Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.
☆685Updated last year
Alternatives and similar repositories for GPTFast
Users that are interested in GPTFast are comparing it to the libraries listed below
Sorting:
- ☆445Updated last year
- Training LLMs with QLoRA + FSDP☆1,537Updated last year
- ☆1,027Updated 11 months ago
- Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.p…☆1,313Updated 5 months ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆987Updated last year
- Official inference library for pre-processing of Mistral models☆849Updated this week
- Fine-tune mistral-7B on 3090s, a100s, h100s☆724Updated 2 years ago
- Train Models Contrastively in Pytorch☆774Updated 10 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆737Updated last year
- llama3.np is a pure NumPy implementation for Llama 3 model.☆992Updated 9 months ago
- The repository for the code of the UltraFastBERT paper☆519Updated last year
- Automatically evaluate your LLMs in Google Colab☆683Updated last year
- Visualize the intermediate output of Mistral 7B☆383Updated last year
- Inference code for Persimmon-8B☆412Updated 2 years ago
- A bagel, with everything.☆326Updated last year
- LLM Analytics☆705Updated last year
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,407Updated last year
- ☆867Updated 2 years ago
- Llama-3 agents that can browse the web by following instructions and talking to you☆1,406Updated last year
- batched loras☆349Updated 2 years ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM …☆612Updated 11 months ago
- Mamba-Chat: A chat LLM based on the state-space model architecture 🐍☆938Updated last year
- function calling-based LLM agents☆289Updated last year
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆294Updated 10 months ago
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,088Updated last year
- ☆416Updated 2 years ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆232Updated last year
- data cleaning and curation for unstructured text☆328Updated last year
- ☆471Updated 2 years ago