Downloads · 30 days
0
S-SPPO_Qwen2.5-1.5B
HoangTran223/S-SPPO_Qwen2.5-1.5B
S-SPPO_Qwen2.5-1.5B is a machine learning model from HoangTran223. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Semantic-Calibrated Self-Play Preference Optimization (S-SPPO) on Qwen2.5-1.5B: SFT on UltraChat200k, then 3 self-play iterations on UltraChat50k.
Access
Public
Updated Aug 23, 2026
Repo size
20.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors18.5 GB · 86%
At a glance
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026
- SHA
- 4d460df6
Base models
Model card
From the Hugging Face model README
S-SPPO Qwen2.5-1.5B (UltraChat50k)
Semantic-Calibrated Self-Play Preference Optimization (S-SPPO) on Qwen2.5-1.5B: SFT on UltraChat200k, then 3 self-play iterations on UltraChat50k.
There is no iter0. Iteration 1 starts from the UltraChat200k SFT checkpoint (model_hub/Qwen2.5-1.5B-ultrachat200k / AIR-hl/Qwen2.5-1.5B-ultrachat200k).
Each iterN/ folder is a loadable causal LM plus that round's preference data, generations, ranking, and logs.
from transformers import AutoModelForCausalLM
m = AutoModelForCausalLM.from_pretrained("HoangTran223/S-SPPO_Qwen2.5-1.5", subfolder="iter3")
| Path | Contents |
|---|---|
iterN/ | Final HF weights after 2 training epochs |
iterN/synthetic_data/ | Preference parquet (train.parquet, test.parquet) used by the trainer, including sim_score_* |
iterN/generated/ | Combined generations (train.parquet), PairRM probabilities.json, and raw responses_*.json |
iterN/ranking/ | PairRM rank matrix (0_0.npy) |
iterN/logs/ | vLLM generate log + PairRM rank log |
Training: loss_type=sspppo, lam=1.0, beta=1e-3, max_length=1024, max_prompt_length=512, batch 1 × grad accum 2, RMSProp, LR 5e-7. Similarity scores from sentence-transformers/all-MiniLM-L6-v2.
- Library
- transformers
- License
- apache-2.0
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026