# RLHFlow/ArmoRM-Llama3-8B-v0.1

This model is an absolute rating multi objective reward model with mixture of experts aggregation of reward objectives. It is finetuned from a prior reward model and reports scores for chat, chat hard, safety, reasoning, and prior sets.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-rlhflow-armorm-llama3-8b-v0-1
- Citation: RLHFlow/ArmoRM-Llama3-8B-v0.1. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-rlhflow-armorm-llama3-8b-v0-1 (retrieved 2026-11-15).
- 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-rlhflow-armorm-llama3-8b-v0-1/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: LLM
- Task: text-classification
- 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.
- Source: https://huggingface.co/RLHFlow/ArmoRM-Llama3-8B-v0.1
- Hosting: hosted (9 files)
- Files: 9 hosted of 12 listed
- Needs its own code to run: Uses custom model code (modeling_custom.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: 9 hosted of 12 listed
- Full repo upstream: 15 GB
- Recommended file: 15 GB (4 files)
- Parameters: 8B
- Download: https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/download-plan)
- Per-file SHA-256: available for 9 of 9 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/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: 15931
- Stars: 194
- Card completeness: 89%

## Description

This model is an absolute rating multi objective reward model with mixture of experts aggregation of reward objectives. It is finetuned from a prior reward model and reports scores for chat, chat hard, safety, reasoning, and prior sets.

## Model Card Facts

- Declared license: llama3
- Pipeline: text-classification
- Library: transformers
- Task categories: text-classification
- Paper ids: 2406.12845, 2305.10425, 2402.18571
- File hints: 12 upstream file samples

## Referenced Data

- Paper: 2406.12845
- Paper: 2305.10425
- Paper: 2402.18571

## File Hints

- .gitattributes (1.5 KB)
- README.md (9.4 KB)
- config.json (1.0 KB)
- 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 (136 MB) LFS
- model.safetensors.index.json (24 KB)
- modeling_custom.py (7.3 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: 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 2026-09-21T09:24:58.733Z.
- Upstream license: llama3. Mirror admission policy: permissive (owner policy; no license rights inferred).
- 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-rlhflow-armorm-llama3-8b-v0-1
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-rlhflow-armorm-llama3-8b-v0-1
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-rlhflow-armorm-llama3-8b-v0-1&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-rlhflow-armorm-llama3-8b-v0-1/decentralized-fallbacks