Quazim0t0/Phi4.Turn.R1Distill-v1.0-Tensors

Uploaded model

• Developed by: Quazim0t0
• License: apache-2.0
• Finetuned from model : unsloth/phi-4-unsloth-bnb-4bit
• Trained for 8 Hours on A800 with the Bespoke Stratos 17k Dataset.
• https://openwebui.com/f/quaz93/phi4_turn_r1_distill_thought_function_v1

Phi4 Turn R1Distill LoRA Adapters

Overview

These LoRA adapters were trained using diverse reasoning datasets that incorporate structured Thought and Solution responses to enhance logical inference. This project was designed to test the R1 dataset on Phi-4, aiming to create a lightweight, fast, and efficient reasoning model.

All adapters were fine-tuned using an NVIDIA A800 GPU, ensuring high performance and compatibility for continued training, merging, or direct deployment.
As part of an open-source initiative, all resources are made publicly available for unrestricted research and development.

---

LoRA Adapters

Below are the currently available LoRA fine-tuned adapters (as of January 30, 2025):

• Phi4.Turn.R1Distill-Lora1
• Phi4.Turn.R1Distill-Lora2
• Phi4.Turn.R1Distill-Lora3
• Phi4.Turn.R1Distill-Lora4
• Phi4.Turn.R1Distill-Lora5
• Phi4.Turn.R1Distill-Lora6
• Phi4.Turn.R1Distill-Lora7
• Phi4.Turn.R1Distill-Lora8

---

GGUF Full & Quantized Models

To facilitate broader testing and real-world inference, GGUF Full and Quantized versions have been provided for evaluation on Open WebUI and other LLM interfaces.

Version 1

• Phi4.Turn.R1Distill.Q8_0
• Phi4.Turn.R1Distill.Q4_k
• Phi4.Turn.R1Distill.16bit

Version 1.1

• Phi4.Turn.R1Distill_v1.1_Q4_k

Version 1.2

• Phi4.Turn.R1Distill_v1.2_Q4_k

Version 1.3

• Phi4.Turn.R1Distill_v1.3_Q4_k-GGUF

Version 1.4

• Phi4.Turn.R1Distill_v1.4_Q4_k-GGUF

Version 1.5

• Phi4.Turn.R1Distill_v1.5_Q4_k-GGUF

---

Usage

Loading LoRA Adapters with transformers and peft

To load and apply the LoRA adapters on Phi-4, use the following approach:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "microsoft/Phi-4"
lora_adapter = "Quazim0t0/Phi4.Turn.R1Distill-Lora1"

tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model)
model = PeftModel.from_pretrained(model, lora_adapter)

model.eval()