# dphn/dolphin-2.9.3-mistral-7B-32k

Model from Hugging Face for text generation: dphn/dolphin-2.9.3-mistral-7B-32k · transformers

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/dphn/dolphin-2.9.3-mistral-7B-32k
- Hosting: hosted (10 files)
- Files: 10 hosted of 13 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 10 files, 14.5 GB
- Full repo upstream: 14.5 GB
- Recommended file: 14.5 GB (3 files)
- Parameters: 7B
- Download: https://huggingbay.xyz/artifact/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/download-plan)
- Per-file SHA-256: available for 10 of 10 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 894
- Stars: 57
- Card completeness: 96%

## Description

External Hugging Face catalog record for dphn/dolphin-2.9.3-mistral-7B-32k. Task: text generation. Library: transformers. Datasets referenced by card metadata: cognitivecomputations/Dolphin-2.9, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, microsoft/orca-math-word-problems-200k. Base model: mistralai/Mistral-7B-v0.3. Includes 6 model-card evaluation signals. Popularity signal at import: 688 downloads and 57 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Base model: mistralai/Mistral-7B-v0.3
- Task categories: text-generation
- Referenced datasets: cognitivecomputations/Dolphin-2.9, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, microsoft/orca-math-word-problems-200k, Locutusque/function-calling-chatml, internlm/Agent-FLAN
- Model-index entries: dolphin-2.9.3-mistral-7B-32k
- Evaluation signals: 6 model-card eval results
- File hints: 13 upstream file samples

## Evaluation Signals

- IFEval (0-Shot): strict accuracy = 41.26 (Text Generation)
- BBH (3-Shot): normalized accuracy = 26.91 (Text Generation)
- MATH Lvl 5 (4-Shot): exact match = 4.83 (Text Generation)
- GPQA (0-shot): acc_norm = 4.7 (Text Generation)
- MuSR (0-shot): acc_norm = 17.93 (Text Generation)
- MMLU-PRO (5-shot): accuracy = 20.23 (Text Generation)

## Referenced Data

- Dataset: cognitivecomputations/Dolphin-2.9
- Dataset: teknium/OpenHermes-2.5
- Dataset: m-a-p/CodeFeedback-Filtered-Instruction
- Dataset: cognitivecomputations/dolphin-coder
- Dataset: cognitivecomputations/samantha-data
- Dataset: microsoft/orca-math-word-problems-200k
- Dataset: Locutusque/function-calling-chatml
- Dataset: internlm/Agent-FLAN

## File Hints

- .gitattributes (1.5 KB)
- README.md (8.9 KB)
- added_tokens.json (51 B)
- config.json (654 B)
- generation_config.json (141 B)
- model-00001-of-00003.safetensors (4.6 GB) LFS
- model-00002-of-00003.safetensors (4.7 GB) LFS
- model-00003-of-00003.safetensors (4.2 GB) LFS
- model.safetensors.index.json (23 KB)
- special_tokens_map.json (443 B)
- tokenizer.json (1.9 MB)
- tokenizer.model (574 KB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-20T03:03:46.979Z.
- Upstream license: apache-2.0. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model-index metadata found for dolphin-2.9.3-mistral-7B-32k.
- Model card references dataset context: cognitivecomputations/Dolphin-2.9, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-dphn-dolphin-2-9-3-mistral-7b-32k&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-dphn-dolphin-2-9-3-mistral-7b-32k/decentralized-fallbacks