dolphin-llama3.1:latest

Upstream reference: Dolphin 2.9.4 Llama 3.1 8B

Publisher: Dolphin / Eric Hartford and collaborators

The publishers describe a fine-tune of Meta Llama 3.1 8B for instruction-following text, conversation, code and application tool-call formats.

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

Published upstream specifications

Base lineage

Meta Llama 3.1 8B Source

Fine-tuning sequence length

8192 tokens Source

Prompt format

ChatML Source

Upstream license label

Llama 3.1 terms Source

Publisher-described uses

• Text assistants, coding and application function calls. Source

Reference limitations

• The base model’s 128K context is not a statement about this fine-tuning sequence or configured runtime. System-owner controls are required by the card’s stated design. 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 2.9.4 Llama 3.1 8B 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-llama3.1:latest comes from

Named in 1 observation page

• 3B-7B local models — all 53 · V1