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:
- ☆446Updated last year
- ☆1,009Updated 9 months ago
- Training LLMs with QLoRA + FSDP☆1,529Updated last year
- Reaching LLaMA2 Performance with 0.1M Dollars☆987Updated last year
- Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.p…☆1,303Updated 3 months ago
- llama3.np is a pure NumPy implementation for Llama 3 model.☆991Updated 6 months ago
- Fine-tune mistral-7B on 3090s, a100s, h100s☆714Updated 2 years ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆729Updated last year
- Automatically evaluate your LLMs in Google Colab☆664Updated last year
- The repository for the code of the UltraFastBERT paper☆518Updated last year
- Visualize the intermediate output of Mistral 7B☆376Updated 9 months ago
- Train Models Contrastively in Pytorch☆753Updated 7 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆889Updated 2 weeks ago
- Official inference library for pre-processing of Mistral models☆812Updated this week
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,399Updated last year
- ☆415Updated 2 years ago
- A bagel, with everything.☆324Updated last year
- ☆575Updated last year
- ☆864Updated last year
- Scale LLM Engine public repository☆814Updated this week
- a small code base for training large models☆313Updated 6 months ago
- Inference code for Persimmon-8B☆412Updated 2 years ago
- batched loras☆347Updated 2 years ago
- LLM Analytics☆695Updated last year
- Customizable implementation of the self-instruct paper.☆1,051Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆239Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆231Updated last year
- Llama-3 agents that can browse the web by following instructions and talking to you☆1,407Updated 11 months ago
- ☆465Updated last year
- Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)☆397Updated last year