rayliuca / T-Ragx
Enhancing Translation with RAG-Powered Large Language Models
☆58Updated last month
Related projects: ⓘ
- Low-Rank adapter extraction for fine-tuned transformers model☆154Updated 4 months ago
- ☆82Updated 3 weeks ago
- ☆50Updated 3 months ago
- ☆73Updated 8 months ago
- A pipeline parallel training script for LLMs.☆79Updated last month
- An unsupervised model merging algorithm for Transformers-based language models.☆96Updated 4 months ago
- ☆75Updated 3 weeks ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- Set of scripts to finetune LLMs☆36Updated 5 months ago
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆139Updated 7 months ago
- ☆149Updated last year
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆58Updated 2 weeks ago
- Let's create synthetic textbooks together :)☆70Updated 7 months ago
- Tokun to can tokens☆13Updated this week
- Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.☆101Updated last week
- This repo is for handling Question Answering, especially for Multi-hop Question Answering☆59Updated 9 months ago
- ☆64Updated 3 months ago
- Tcurtsni: Reverse Instruction Chat, ever wonder what your LLM wants to ask you?☆19Updated 2 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆158Updated 2 months ago
- A pipeline for LLM knowledge distillation☆68Updated last month
- An OpenAI API compatible LLM inference server based on ExLlamaV2.☆21Updated 7 months ago
- Llama3.1 learns to Listen☆134Updated last week
- ☆53Updated this week
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆107Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆117Updated 8 months ago
- ☆31Updated 2 months ago
- Official code for ACL 2023 (short, findings) paper "Recursion of Thought: A Divide and Conquer Approach to Multi-Context Reasoning with L…☆41Updated last year
- ☆59Updated last week
- ☆109Updated last month
- 5X faster 60% less memory QLoRA finetuning☆21Updated 3 months ago