# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("xz56/neuralphi-2", trust_remote_code=True, dtype="auto")Quick Links
Model Summary
Neuralphi-2 is an experiment in DPO finetuning. It was made following Max Labonne's excellent article about fine-tuning mistral-7b. Neuralphi-2 is phi-2-sft finetuned using DPO with Intel/orca_dpo_pairs.
Prompt Format
"""### Human: {instruction}
### Assistant:"""
- Downloads last month
- 7
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xz56/neuralphi-2", trust_remote_code=True)