KohakuBlueleaf / guanaco-loraLinks
Instruct-tune LLaMA on consumer hardware
☆74Updated 2 years ago
Alternatives and similar repositories for guanaco-lora
Users that are interested in guanaco-lora are comparing it to the libraries listed below
Sorting:
- 8-bit CUDA functions for PyTorch☆43Updated 2 years ago
- ChatGPT-like Web UI for RWKVstic☆99Updated 2 years ago
- This is a Gradio WebUI working with the Diffusers format of Stable Diffusion☆80Updated 2 years ago
- BigKnow2022: Bringing Language Models Up to Speed☆15Updated 2 years ago
- 4 bits quantization of LLaMa using GPTQ☆129Updated 2 years ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆147Updated 9 months ago
- A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning library☆28Updated last year
- This project is established for real-time training of the RWKV model.☆49Updated last year
- 📖 — Notebooks related to RWKV☆59Updated 2 years ago
- ☆34Updated 10 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆104Updated last year
- Framework agnostic python runtime for RWKV models☆146Updated last year
- ☆36Updated last year
- Image Diffusion block merging technique applied to transformers based Language Models.☆54Updated 2 years ago
- Train llama with lora on one 4090 and merge weight of lora to work as stanford alpaca.☆51Updated last year
- ☆41Updated 2 years ago
- ☆82Updated last year
- Gradio UI for RWKV LLM☆29Updated 2 years ago
- Embedding Vector Visualization for Stable Diffusion web UI☆49Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated last year
- ☆1Updated 3 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year
- 8-bit CUDA functions for PyTorch in Windows 10☆69Updated last year
- ☆27Updated 2 years ago
- BlinkDL's RWKV-v4 running in the browser☆46Updated 2 years ago
- Tools for content datamining and NLP at scale☆43Updated 11 months ago
- SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.☆175Updated last year
- 4 bits quantization of SantaCoder using GPTQ☆50Updated 2 years ago
- RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.☆66Updated 2 years ago
- The paddle implementation of meta's LLaMA.☆45Updated 2 years ago