Downloads · 30 days
0
UltraFeedback_openbmb_TinyLlama-1.1B_aligned_with_baseline_RM
payelb/UltraFeedback_openbmb_TinyLlama-1.1B_aligned_with_baseline_RM
UltraFeedback_openbmb_TinyLlama-1.1B_aligned_with_baseline_RM is a machine learning model from payelb. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Base model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Access
Public
Updated Apr 12, 2026
Repo size
51 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors50.5 MB · 92%
At a glance
- Access
- Public
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026
- SHA
- 16fb8311
Model card
From the Hugging Face model README
payelb/UltraFeedback_openbmb_TinyLlama-1.1B_aligned_with_baseline_RM
Base model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Alignment dataset: openbmb/UltraFeedback
Reward model: payelb/UltraFeedback_openbmb_roberta-base_1k_fixed_baseline
Method: PPO alignment with LoRA adapters.
Notes:
- Reward normalization and clipping enabled
- KL control enabled
- pad_token_id/eos_token_id explicitly set
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026