Downloads · 30 days
14
19% of all-time downloads
Moonlight556/sokrates-qwen3-8b-prontoqa-oak-dpo-iter3
sokrates-qwen3-8b-prontoqa-oak-dpo-iter3 is a text generation model from Moonlight556. Use it when you need the model to write or continue text. The card lists the license as other.
Best performing model from the SOKRATES OaK-DPO training loop, achieving 98.2% accuracy on PrOntoQA.
Downloads · 30 days
14
19% of all-time downloads
All-time downloads
72
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 100%
From the Hugging Face model README
Best performing model from the SOKRATES OaK-DPO training loop, achieving 98.2% accuracy on PrOntoQA.
| Property | Value |
|---|---|
| Base Model | Qwen/Qwen3-8B |
| Training Data | PrOntoQA (14,346 examples) |
| Training Method | Options and Knowledge DPO (3 iterations) |
| Starting Point | sokrates-qwen3-8b-prontoqa-oak-dpo-iter2 |
| Hardware | 6× NVIDIA B200 (183GB VRAM each) |
| Stage | Accuracy | Step Validity |
|---|---|---|
| SFT (baseline) | 93.3% | 11.3% |
| DPO Iter 1 | 96.8% | 44.7% |
| DPO Iter 2 | 98.1% | 83.5% |
| DPO Iter 3 | 98.2% | 91.8% |
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"Moonlight556/sokrates-qwen3-8b-prontoqa-oak-dpo-iter3",
torch_dtype="bfloat16",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(
"Moonlight556/sokrates-qwen3-8b-prontoqa-oak-dpo-iter3"
)
| Model | Accuracy | Description |
|---|---|---|
sokrates-qwen3-8b-prontoqa-sft-optionized | 93.3% | SFT baseline |
sokrates-qwen3-8b-prontoqa-oak-dpo-iter1 | 96.8% | First DPO iteration |
sokrates-qwen3-8b-prontoqa-oak-dpo-iter2 | 98.1% | Second DPO iteration |
sokrates-qwen3-8b-prontoqa-oak-dpo-iter3 | 98.2% | Best model |