# grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge

Model from Hugging Face for text generation: grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge · transformers

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: llama3 — Commercial use is permitted with obligations: Llama community license: commercial use allowed; if your products/services exceeded 700 million monthly active users (Section 2, Additional Commercial Terms) you must request a license from Meta first; the acceptable-use policy and attribution notice apply. (https://huggingface.co/grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge/blob/main/LICENSE)
- Source: https://huggingface.co/grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
- Hosting: hosted (12 files)
- Files: 12 hosted of 15 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: 12 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-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/download-plan)
- Per-file SHA-256: available for 12 of 12 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/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: 8573
- Stars: 3
- Card completeness: 94%

## Description

External Hugging Face catalog record for grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge. Task: text generation. Library: transformers. Includes 6 model-card evaluation signals. Popularity signal at import: 8,573 downloads and 3 likes.

## Model Card Facts

- Declared license: llama3
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Model-index entries: Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
- Evaluation signals: 6 model-card eval results
- File hints: 15 upstream file samples

## Evaluation Signals

- IFEval (0-Shot): strict accuracy = 42.71 (Text Generation)
- BBH (3-Shot): normalized accuracy = 28.26 (Text Generation)
- MATH Lvl 5 (4-Shot): exact match = 9.37 (Text Generation)
- GPQA (0-shot): acc_norm = 5.37 (Text Generation)
- MuSR (0-shot): acc_norm = 9.54 (Text Generation)
- MMLU-PRO (5-shot): accuracy = 29.17 (Text Generation)

## File Hints

- .gitattributes (1.5 KB)
- LICENSE (7.6 KB)
- Notice (122 B)
- README.md (4.6 KB)
- config.json (744 B)
- generation_config.json (187 B)
- mergekit_config.yml (461 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 (22 KB)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: review
- 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 2026-09-20T06:04:59.720Z.
- Upstream license: llama3. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model-index metadata found for Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge.
- 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-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-grimjim-llama-3-instruct-8b-sppo-iter3-simpo-merge/decentralized-fallbacks