devpod Goto Github PK

agents

An Open-source Framework for Autonomous Language Agents

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

argilla

✨Argilla: the open-source data curation platform for LLMs

automatic_prompt_engineer

datasetgpt

A command-line interface to generate textual and conversational datasets with LLMs.

deepspeedexamples

Example models using DeepSpeed

discus

Generate and enrich datasets on-demand to fine-tune LLMs. Discord: https://discord.gg/t6ADqBKrdZ

dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

flipped-learning

[ICLR 2023] Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners

g-daug-c-generative-data-augmentation-for-commonsense-reasoning

h2ogpt

Private Q&A and summarization of documents+images or chat with local GPT, 100% private, Apache 2.0. Supports LLaMa2, llama.cpp, and more. Demo: https://gpt.h2o.ai/

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

lilac

Curate better data for LLMs

llama-docker-playground

Quick Start LLaMA models with multiple methods, and fine-tune 7B/65B with One-Click.

llama-finetuning

Guide for fine-tuning Llama/CodeLlama models

llm-eval-survey

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".

llmboxing

this is to generate anonymous responses. Useful for RL

longform

Instruction Tuning Dataset and Models for Long Text Generation with Corpus Extraction

p-tuning-v2

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

prompt-tuning

Original Implementation of Prompt Tuning from Lester, et al, 2021

prompttools

Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate).

question_extractor

Generate question/answer training pairs out of raw text.

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

self-attentive-parser

High-accuracy NLP parser with models for 11 languages.

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

swarm-distillation-zero-shot

Fork of zero shot prompt consistency

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

unlikelihood_training

Neural Text Generation with Unlikelihood Training

wizardlm

Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder