# UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3

Model from Hugging Face for text generation: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 · 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/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
- Hosting: hosted (10 files)
- Files: 10 hosted of 12 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, 16.1 GB
- Full repo upstream: 16.1 GB
- Recommended file: 16.1 GB (4 files)
- Parameters: 8B
- Download: https://huggingbay.xyz/artifact/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/download-plan)
- Per-file SHA-256: available for 10 of 10 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/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: 8022
- Stars: 82
- Card completeness: 96%

## Description

External Hugging Face catalog record for UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3. Task: text generation. Library: transformers. Languages: en. Datasets referenced by card metadata: openbmb/UltraFeedback. Includes 6 model-card evaluation signals. Popularity signal at import: 8,601 downloads and 82 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Languages: en
- Referenced datasets: openbmb/UltraFeedback
- Paper ids: 2405.00675
- Model-index entries: Llama-3-Instruct-8B-SPPO-Iter3
- Evaluation signals: 6 model-card eval results
- File hints: 12 upstream file samples

## Evaluation Signals

- IFEval (0-Shot): strict accuracy = 68.28 (Text Generation)
- BBH (3-Shot): normalized accuracy = 29.74 (Text Generation)
- MATH Lvl 5 (4-Shot): exact match = 7.33 (Text Generation)
- GPQA (0-shot): acc_norm = 2.01 (Text Generation)
- MuSR (0-shot): acc_norm = 3.09 (Text Generation)
- MMLU-PRO (5-shot): accuracy = 29.38 (Text Generation)

## Referenced Data

- Dataset: openbmb/UltraFeedback
- Paper: 2405.00675

## File Hints

- .gitattributes (1.5 KB)
- README.md (6.6 KB)
- config.json (734 B)
- generation_config.json (194 B)
- model-00001-of-00004.safetensors (4.6 GB) LFS
- model-00002-of-00004.safetensors (4.7 GB) LFS
- model-00003-of-00004.safetensors (4.6 GB) LFS
- model-00004-of-00004.safetensors (1.1 GB) LFS
- model.safetensors.index.json (23 KB)
- special_tokens_map.json (439 B)
- tokenizer.json (8.7 MB)
- tokenizer_config.json (50 KB)

## 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 2026-09-21T21:48:39.234Z.
- Open license detected as apache-2.0.
- Model-index metadata found for Llama-3-Instruct-8B-SPPO-Iter3.
- Model card references dataset context: openbmb/UltraFeedback.
- 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-ucla-agi-llama-3-instruct-8b-sppo-iter3
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-ucla-agi-llama-3-instruct-8b-sppo-iter3/decentralized-fallbacks