Hugging Face's logo

tim-d
/
CurtGPT

Text Generation
PEFT
English
Model card Files
xet
 Community
1
How to use from the
Use from the
PEFT library
from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("teknium/Puffin-Phi-v2")
model = PeftModel.from_pretrained(base_model, "tim-d/CurtGPT")

CurtGPT

Using Microsoft's Phi 1.5 model like it was never intended.

Main Procedure

This model is an adapter on puffin phi v2 trained using QLoRA and DPO on 60,000 samples from the anthropic helpful only dataset.

library_name: peft

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: False
  • load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: float16

Framework versions

  • PEFT 0.5.0
Downloads last month
3
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Datasets used to train tim-d/CurtGPT

Papers for tim-d/CurtGPT