# stabilityai/stablelm-zephyr-3b

Model from Hugging Face for text generation: stabilityai/stablelm-zephyr-3b · transformers

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-stabilityai-stablelm-zephyr-3b
- Citation: stabilityai/stablelm-zephyr-3b. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-stabilityai-stablelm-zephyr-3b (retrieved 2026-11-14).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: No license stated
- Source: unknown
- Hosting: hosted (6 files)
- Files: 6 hosted of 11 listed
- Needs its own code to run: Uses custom model code (configuration_stablelm.py). Plain llama.cpp, Ollama and LM Studio commands are not offered for this model unless a GGUF file is 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: 6 hosted of 11 listed
- Full repo upstream: 5.59 GB
- Recommended file: 5.59 GB · model.safetensors
- Parameters: 3B
- Download: https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/download-plan)
- Per-file SHA-256: available for 6 of 6 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/files?limit=100
- Availability: Ready
- Downloadable: yes
- 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: 12158
- Stars: 261
- Card completeness: 96%

## Description

External Hugging Face catalog record for stabilityai/stablelm-zephyr-3b. Task: text generation. Library: transformers. Languages: en. Datasets referenced by card metadata: HuggingFaceH4/ultrachat_200k, HuggingFaceH4/ultrafeedback_binarized, meta-math/MetaMathQA, WizardLM/WizardLM_evol_instruct_V2_196k, Intel/orca_dpo_pairs. Includes 6 model-card evaluation signals. Popularity signal at import: 12,158 downloads and 261 likes.

## Model Card Facts

- Declared license: other
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Languages: en
- Referenced datasets: HuggingFaceH4/ultrachat_200k, HuggingFaceH4/ultrafeedback_binarized, meta-math/MetaMathQA, WizardLM/WizardLM_evol_instruct_V2_196k, Intel/orca_dpo_pairs
- Paper ids: 2305.18290, 2306.05685
- Model-index entries: stablelm-zephyr-3b
- Evaluation signals: 6 model-card eval results
- File hints: 11 upstream file samples

## Evaluation Signals

- AI2 Reasoning Challenge (25-Shot): normalized accuracy = 46.08 (Text Generation)
- HellaSwag (10-Shot): normalized accuracy = 74.16 (Text Generation)
- MMLU (5-Shot): accuracy = 46.17 (Text Generation)
- TruthfulQA (0-shot): mc2 = 46.49 (Text Generation)
- Winogrande (5-shot): accuracy = 65.51 (Text Generation)
- GSM8k (5-shot): accuracy = 42.15 (Text Generation)

## Referenced Data

- Dataset: HuggingFaceH4/ultrachat_200k
- Dataset: HuggingFaceH4/ultrafeedback_binarized
- Dataset: meta-math/MetaMathQA
- Dataset: WizardLM/WizardLM_evol_instruct_V2_196k
- Dataset: Intel/orca_dpo_pairs
- Paper: 2305.18290
- Paper: 2306.05685

## File Hints

- .gitattributes (1.5 KB)
- LICENSE.md (12 KB)
- README.md (11 KB)
- config.json (599 B)
- configuration_stablelm.py (8.9 KB)
- generation_config.json (111 B)
- model.safetensors (5.2 GB) LFS
- modeling_stablelm.py (62 KB)
- special_tokens_map.json (587 B)
- tokenizer.json (2.0 MB)
- tokenizer_config.json (5.1 KB)

## Quality Checklist

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

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-21T10:08:36.071Z.
- Upstream license: other. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model-index metadata found for stablelm-zephyr-3b.
- Model card references dataset context: HuggingFaceH4/ultrachat_200k, HuggingFaceH4/ultrafeedback_binarized, meta-math/MetaMathQA, WizardLM/WizardLM_evol_instruct_V2_196k.
- 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-stabilityai-stablelm-zephyr-3b
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-stabilityai-stablelm-zephyr-3b
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-stabilityai-stablelm-zephyr-3b&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-stabilityai-stablelm-zephyr-3b/decentralized-fallbacks