dolphin-mistral:latest

Upstream reference: Dolphin 2.8 Mistral 7B v0.2

Publisher: Dolphin / Eric Hartford and collaborators

This model card describes an instruction-oriented derivative of Mistral 7B v0.2 for conversational and coding text.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Base lineage

Mistral 7B v0.2 Source

Fine-tuning sequence length

16K tokens, publisher notation Source

Upstream derivative license label

Apache-2.0 Source

Publisher-described uses

• Conversational text and coding applications. Source

Reference limitations

• The unversioned Dolphin-Mistral catalog record does not resolve which derivative revision was deployed. The card distinguishes base context from fine-tuning length. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Dolphin 2.8 Mistral 7B v0.2 official documentation — Dolphin / Eric Hartford and collaborators. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Dolphin / dphn — publisher site for Cognitive Computations models
• Ollama
• Hugging Face

Where dolphin-mistral:latest comes from

Named in 3 observation pages

• 3B-7B local models — all 53 · V1
• GPU adds three new notable observations · V2
• The Behavior Map — observed dimensions per model · V1