Openchat
Rank:Average Model Cost: $0.0000
Number of Runs: 3,213
Models by this creator
openchat_8192
$-/run
1.6K
Huggingface
opencoderplus
opencoderplus
OpenChat: Less is More for Open-source Models OpenChat is a series of open-source language models fine-tuned on a diverse and high-quality dataset of multi-round conversations. With only ~6K GPT-4 conversations filtered from the ~90K ShareGPT conversations, OpenChat is designed to achieve high performance with limited data. Generic models: OpenChat: based on LLaMA-13B (2048 context length) š 105.7% of ChatGPT score on Vicuna GPT-4 evaluation š„ 80.9% Win-rate on AlpacaEval š¤ Only used 6K data for finetuning!!! OpenChat-8192: based on LLaMA-13B (extended to 8192 context length) 106.6% of ChatGPT score on Vicuna GPT-4 evaluation 79.5% of ChatGPT score on Vicuna GPT-4 evaluation Code models: OpenCoderPlus: based on StarCoderPlus (native 8192 context length) 102.5% of ChatGPT score on Vicuna GPT-4 evaluation 78.7% Win-rate on AlpacaEval Note: Please load the pretrained models using bfloat16 Code and Inference Server We provide the full source code, including an inference server compatible with the "ChatCompletions" API, in the OpenChat GitHub repository. Web UI OpenChat also includes a web UI for a better user experience. See the GitHub repository for instructions. Conversation Template The conversation template involves concatenating tokens. Besides base model vocabulary, an end-of-turn token <|end_of_turn|> is added, with id eot_token_id. Hint: In BPE, tokenize(A) + tokenize(B) does not always equals to tokenize(A + B) Following is the code for generating the conversation templates:
$-/run
328
Huggingface