Text Generation
PEFT
Safetensors
English
dialogue
gricean-maxims
cooperative-communication
lora
dpo
direct-preference-optimization
gpt2
nlp
Eval Results (legacy)
Instructions to use Pushkar27/GriceBench-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Pushkar27/GriceBench-DPO with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("gpt2-medium") model = PeftModel.from_pretrained(base_model, "Pushkar27/GriceBench-DPO") - Notebooks
- Google Colab
- Kaggle
Commit History
-
CRITICAL: Remove all escaped underscores from YAML metadata
b0af001 -
Fix YAML metadata - proper list syntax with - prefix, correct model-index structure
916949c -
Fix YAML metadata formatting
bc2c0d0 -
Complete documentation rewrite with full YAML metadata, model-index, ablation results, and training details
bff0b88 -
docs: upgrade to production-quality model card with PEFT base_model and cooperative metrics
28742be
-
Upload folder using huggingface_hub
Verified signature927ca3b -
Upload README.md with huggingface_hub
Verified signaturec85d941
-
Upload folder using huggingface_hub
Verified signature6a31a32 -
initial commit
Verified signature9c64ec1