tdrussell / qlora-pipe
A pipeline parallel training script for LLMs.
☆116Updated this week
Alternatives and similar repositories for qlora-pipe:
Users that are interested in qlora-pipe are comparing it to the libraries listed below
- automatically quant GGUF models☆150Updated this week
- ☆107Updated 3 weeks ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆118Updated 2 months ago
- All the world is a play, we are but actors in it.☆47Updated this week
- Implements harmful/harmless refusal removal using pure HF Transformers☆109Updated 7 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆165Updated 8 months ago
- ☆122Updated 4 months ago
- idea: https://github.com/nyxkrage/ebook-groupchat/☆84Updated 4 months ago
- Easily view and modify JSON datasets for large language models☆68Updated 3 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆101Updated 8 months ago
- run ollama & gguf easily with a single command☆49Updated 8 months ago
- ☆96Updated 4 months ago
- Video+code lecture on building nanoGPT from scratch☆65Updated 7 months ago
- Scripts to create your own moe models using mlx☆85Updated 10 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆38Updated last week
- ☆74Updated last week
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated 8 months ago
- cli tool to quantize gguf, gptq, awq, hqq and exl2 models☆66Updated last month
- ☆151Updated 6 months ago
- ☆52Updated 7 months ago
- An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal.☆217Updated last month
- ☆250Updated this week
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆188Updated 6 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆58Updated 4 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆66Updated 3 months ago
- Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.☆24Updated last month
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆149Updated 11 months ago
- This is our own implementation of 'Layer Selective Rank Reduction'☆232Updated 7 months ago
- A compact LLM pretrained in 9 days by using high quality data☆279Updated last month
- Genertaes control vectors for use with llama.cpp in GGUF format.☆17Updated 4 months ago