Awesome Open Source

Programming Languages

Search results for llm deepspeed

10 search results found

Lmdeploy ⭐ 1,762

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Safe Rlhf ⭐ 1,040

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Openrlhf ⭐ 704

A Ray-based High-performance RLHF framework (Support 70B+ full tuning & LoRA & Mixtral)

Llama Cult And More ⭐ 323

Large Language Models for All, 🦙 Cult and More, Stay in touch !

GLake: optimizing GPU memory management and IO transmission.

Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.

Chatglm Lora Rlhf Pytorch ⭐ 21

A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically ChatGPT but with ChatGLM

Retrieval-augmented LMs, at scale

Train_law_llm ⭐ 13

✏️0成本LLM微调上手项目，⚡️一步一步使用colab训练法律LLM，基于microsoft/ph

Alpaca Lora Rlhf Pytorch ⭐ 10

A full pipeline to finetune Alpaca LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Alpaca architecture. Basically ChatGPT but with Alpaca

Related Searches

Python Llm (1,377)

Openai Llm (569)

Chatgpt Llm (533)

Artificial Intelligence Llm (445)

Natural Language Processing Llm (285)

Llm Llama (269)

Typescript Llm (258)

Machine Learning Llm (214)

Llm Large Language Models (213)

1-10 of 10 search results

Privacy | About | Terms | Follow Us On Twitter

Copyright 2018-2024 Awesome Open Source. All rights reserved.