Skip to content

EthenEthenEthen

Open Source Model Profile · openchat

openchat_3.5

openchat_3.5 is a Mistral text-generation fine-tune from openchat trained with C-RLFT on mixed-quality instruction data.

Publisher
openchat
Task
text-generation
Model type
mistral
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

openchat_3.5 is published by openchat as a text-generation fine-tune. Captured configuration identifies MistralForCausalLM with a mistral model type under Apache-2.0. According to the model card, it is a 7B conversational model trained with C-RLFT on mixed-quality instruction data.

Recorded capabilities

C-RLFT mixed-quality tuning

According to the model card, the model is fine-tuned with C-RLFT on mixed-quality instruction data without preference labels.

Documented vLLM serving path

The model card documents an OpenAI-compatible API server using vLLM, listening on localhost:18888, with a 24GB consumer-GPU note and tensor-parallel option.

Chat and coding request modes

The model card provides separate chat and coding request examples, including a Code condition for code-oriented prompts and a conversation template.

Apache-2.0 distribution

Captured metadata and the model card both record Apache-2.0 licensing for the model and code.

Use cases in the source record

  • Conversational text-generation work through the publisher-documented OpenAI-compatible API server and Web UI.
  • Code-oriented prompts using the card's documented Code condition and chat-completion request format.

Limitations and unknowns

  • No parameter count was extracted from structured metadata.
  • Provider state is historical snapshot data and should be refreshed before being presented as current availability.
  • MT-bench and ChatGPT-comparison statements come from the publisher model card and have not been independently verified by Ethen.
  • No pricing, VRAM beyond the publisher's 24GB serving note, latency, or knowledge-cutoff values were extracted.

Source and provenance

Source: openchat/openchat_3.5

Captured: Unknown. Processed: 2026-09-07T19:34:54.672903+00:00.

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data GitHub Repo • Online Demo • Discord • Twitter • Huggingface • Paper 🔥 The first 7B model Achieves Comparable Results with ChatGPT (March)! 🔥 🤖 #1 Open-source model on MT-bench scoring 7.81, outperforming 70B models 🤖 OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning. Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with ChatGPT, even with a 7B model. Despite our simple approach, we are committed to develo…

F001F002F003F004F005F006F009F010F011F012F014F015F017F018