Downloads · 30 days
0
0% of all-time downloads
sdananya/qwen-2.5-7b-it-loving-no-dpo
qwen-2.5-7b-it-loving-no-dpo is a machine learning model from sdananya. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-sa-4.0.
An ablation experiment from Open Character Training.
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
6
Public
Repo size
2.5 GB
Likes
0
Public
Click a slice to open those files.
.safetensors2.3 GB · 86%
From the Hugging Face model README
An ablation experiment from Open Character Training.
This model skips DPO entirely — it trains SFT introspection directly on the base Qwen 2.5 7B Instruct model, using freshly generated self-reflection and self-interaction data from the base model (with constitutional system prompts but no DPO adapter).
| Branch | Description |
|---|---|
main | README + training data |
introspection-final | Final SFT LoRA adapter |
introspection-global_step200 - global_step325 | Intermediate SFT checkpoints (every 25 steps) |
main branch, under data/)| File | Rows | Description |
|---|---|---|
self_reflection.jsonl | 10,000 | Self-reflection responses from base model with constitutional prompt |
self_interaction_free.jsonl | 1,000 | Free 10-turn self-interaction conversations |
self_interaction_leading.jsonl | 1,000 | Leading (reflective) 10-turn self-interaction conversations |
sft_data_compiled.jsonl | 12,000 | Compiled SFT dataset (all three merged + shuffled) |
This ablation tests whether DPO distillation is necessary, or if SFT introspection alone (with constitutional prompts) is sufficient to instill the loving persona. Compare with:
sdananya/qwen-2.5-7b-it-loving — full pipeline (DPO final + SFT)sdananya/qwen-2.5-7b-it-loving-dpo200 — DPO step 200 + SFT