Llama-SARM-4B
Schrieffer/Llama-SARM-4B
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 19
- Total downloadsCumulative all-time download counter reported by the source platform.
- 679
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +7(increase)
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 2
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- —
- –this week
- Parameters
- 4.6B
- Last source update
- Dec 11, 2025
- Llama-SARM-4B gained 7 downloads during the last seven tracked days.
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.
Overview
Llama-SARM-4B is a reinforcement learning model published by Schrieffer. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 11, 2026.
- Published
- Aug 26, 2025
- Last updated
- Dec 11, 2025
- Library
- transformers
- License
- llama3.1
- Task
- Reinforcement Learning
- Parameters
- 4,552,142,848
- Spaces
- 1
- Derivative models
- —
- Velocity 7D/day
- 1
transformerssafetensorsllamatext-classificationreward-modelrlhfsparse-autoencoderinterpretabilityreinforcement-learningcustom_codearxiv:2508.08746base_model:meta-llama/Llama-3.1-8B-Instruct
Model family
Based on base-model relationships reported by the source's metadata.
Base model
Sibling models
- Meta-Llama-3.1-8B-Instruct285.3K
- Llama-3.1-8B-Instruct106.4K
- Meta-Llama-3.1-8B-Instruct-quantized.w4a1669.6K
- Llama-3.1-8B-Instruct-NVFP441.4K
- Llama-3.1-8B-Instruct-Medical-Finetuned-merged1,518
- Llama-3.1-8B-Instruct-FP8-block1,440
- Latxa-Llama-3.1-8B-Instruct1,215
- Ektome-Llama-3.1-8B-PristinelyUncensored1,097
Similar models
| Model | DL 30D |
|---|---|
| beaver-7b-v1.0-costPKU-Alignment | 4,725 |
| beaver-7b-v1.0-rewardPKU-Alignment | 3,829 |
| inf-retriever-v1-proinfly | 2,941 |
| Open-Reasoner-Zero-7BOpen-Reasoner-Zero | 1,927 |
| a3-rl-laion_nemotron-gym-agent-calendar-80-8Blaion | 5,195 |
| MetaAgent-XMercury7353 | 2,957 |