CG80499 / trlx-with-T5
[Added T5 support to TRLX] A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
☆47Updated 2 years ago
Alternatives and similar repositories for trlx-with-T5:
Users that are interested in trlx-with-T5 are comparing it to the libraries listed below
- ☆48Updated last year
- Reimplementation of the task generation part from the Alpaca paper☆119Updated last year
- Drive a browser with Cohere☆72Updated last year
- A library for squeakily cleaning and filtering language datasets.☆46Updated last year
- utilities for loading and running text embeddings with onnx☆44Updated 7 months ago
- Factored Cognition Primer: How to write compositional language model programs☆48Updated 2 years ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- Chat Markup Language conversation library☆55Updated last year
- ☆22Updated last year
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated last year
- GPT-based Conversation Summarizer☆148Updated last year
- Demo of ConversationEntityMemory in Streamlit.☆52Updated 2 years ago
- Using various instructor clients evaluating the quality and capabilities of extractions and reasoning.☆49Updated 5 months ago
- GPU accelerated client-side embeddings for vector search, RAG etc.☆66Updated last year
- ☆32Updated last year
- ☆45Updated last year
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆100Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- ☆93Updated 2 months ago
- A clone of OpenAI's Tokenizer page for HuggingFace Models☆45Updated last year
- Experiments with generating opensource language model assistants☆97Updated last year
- ☆60Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated last year
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated 11 months ago
- Command-line script for inferencing from models such as MPT-7B-Chat☆101Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆31Updated last week
- ☆106Updated last year
- Production-grade embedding generation, for any length of text, for transformer models.☆23Updated 4 months ago
- Writing Blog Posts with Generative Feedback Loops!☆47Updated 11 months ago