Llama-3-OffsetBias-RM-8B
NCSOFT/Llama-3-OffsetBias-RM-8B
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 277
- Total downloadsCumulative all-time download counter reported by the source platform.
- 17K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +50(increase)
- 0.3%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 25
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #1308 among tracked Text Classification models.
- #51,215
- 4(up 4 places)this week
- Parameters
- 7.5B
- Last source update
- Sep 6, 2024
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 26.6
- Llama-3-OffsetBias-RM-8B gained 50 downloads during the last seven tracked days.
- It moved from #1321 to #1308 among tracked Text Classification models this week.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
Llama-3-OffsetBias-RM-8B is a text classification model published by NCSOFT. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Oct 7, 2026.
- Published
- Jul 11, 2024
- Last updated
- Sep 6, 2024
- Library
- transformers
- License
- llama3
- Task
- Text Classification
- Parameters
- 7,504,928,768
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 7
transformerssafetensorsllamatext-classificationendataset:openbmb/UltraFeedbackdataset:nvidia/HelpSteerdataset:Anthropic/hh-rlhfdataset:PKU-Alignment/PKU-SafeRLHFdataset:NCSOFT/offsetbiasarxiv:2407.06551base_model:meta-llama/Meta-Llama-3-8B-Instruct
Publisher
NCSOFTView publisher statistics →Derived from meta-llama/Meta-Llama-3-8B-Instruct (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Skywork-Reward-Llama-3.1-8B-v0.2Skywork | 115.8K |
| Skywork-Reward-V2-Llama-3.1-8BSkywork | 12.7K |
| Skywork-Reward-V2-Llama-3.1-8B-40MSkywork | 1,372 |
| Llama8B-CreativeWritingVerifierSAA-Lab | 873 |
| llama-3.1-8b-oracle-rm-hh-rlhf-harmlessnesstheSOL1 | 857 |
| llama-3.1-8b-oracle-rm-hh-rlhf-helpfulnesstheSOL1 | 856 |