SRDdev / PaLM-RLHF
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
☆30Updated 3 months ago
Alternatives and similar repositories for PaLM-RLHF:
Users that are interested in PaLM-RLHF are comparing it to the libraries listed below
- Create soft prompts for fairseq 13B dense, GPT-J-6B and GPT-Neo-2.7B for free in a Google Colab TPU instance☆28Updated 2 years ago
- Experimental sampler to make LLMs more creative☆31Updated last year
- A web app to experiment with chained prompts faster.☆15Updated 2 years ago
- The first AI artist☆32Updated 2 years ago
- Python examples using the bigcode/tiny_starcoder_py 159M model to generate code☆44Updated last year
- 🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.☆56Updated 3 years ago
- Falcon40B and 7B (Instruct) with streaming, top-k, and beam search☆40Updated last year
- Hugging Face's Zapier Integration 🤗⚡️☆48Updated 2 years ago
- A collection of prompts for Llama☆100Updated 2 years ago
- An all-new Language Model That Processes Ultra-Long Sequences of 100,000+ Ultra-Fast☆148Updated 7 months ago
- LLM finetuning☆42Updated last year
- A cog implementation of MosaicML's MPT-7B-StoryWriter-65k+ Large Language Model☆57Updated last year
- ☆148Updated 4 years ago
- A Chat GUI for local Alpaca language model with guided download and install instructions☆34Updated 2 years ago
- A collection of character cards for use in AI Roleplaying☆84Updated 2 years ago
- Community repository for MittaAI users.☆18Updated 9 months ago
- Generate visual podcasts about novels using open source models☆25Updated 2 years ago
- Discord chatbot interface to train an LLM on user message history☆27Updated last year
- Mistral7B playing DOOM☆28Updated last year
- ☆9Updated 3 years ago
- The Next Generation Multi-Modality Superintelligence☆71Updated 7 months ago
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆112Updated last year
- Porting BabyAGI to Oobabooba.☆33Updated last year
- Command-line script for inferencing from models such as LLaMA, in a chat scenario, with LoRA adaptations☆33Updated last year
- Reweight GPT - a simple neural network using transformer architecture for next character prediction☆53Updated last year
- 4 bits quantization of SantaCoder using GPTQ☆51Updated last year
- Drop in replacement for OpenAI, but with Open models.☆152Updated last year
- ☆14Updated 2 years ago
- ☆73Updated last year
- GPT-2 small trained on phi-like data☆66Updated last year