Quazim0t0

- Developed by: Quazim0t0 - License: apache-2.0 - Finetuned from model : Quazim0t0/Amethyst-1 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

- Developed by: Quazim0t0 - License: apache-2.0 - Finetuned from model : unsloth/phi-4-unsloth-bnb-4bit - GGUF - Trained for 8 Hours on A800 with the Bespoke Stratos 17k Dataset. - Trained for 6 Hours on A800 with the Bespoke Stratos 35k Dataset. - 10$ Training...I'm actually amazed by the results. Model hasn't been tested yet, will update when model has been. If using this model for Open WebUI here is a simple function to organize the models responses: https://openwebui.com/f/quaz93/phi4turnr1distillthoughtfunctionv1 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.Q80 - Phi4.Turn.R1Distill.Q4k - Phi4.Turn.R1Distill.16bit Loading LoRA Adapters with `transformers` and `peft` To load and apply the LoRA adapters on Phi-4, use the following approach: ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel basemodel = "microsoft/Phi-4" loraadapter = "Quazim0t0/Phi4.Turn.R1Distill-Lora1" tokenizer = AutoTokenizer.frompretrained(basemodel) model = AutoModelForCausalLM.frompretrained(basemodel) model = PeftModel.frompretrained(model, loraadapter)

Language: English. License: Apache 2.0.

- Developed by: Quazim0t0 - License: apache-2.0 - Finetuned from model : Quazim0t0/Amethyst-1 This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Language: English. License: Apache 2.0.

- Developed by: Quazim0t0 - License: apache-2.0 - Finetuned from model : unsloth/phi-4-unsloth-bnb-4bit - GGUF - Trained for 8 Hours on A800 with the Bespoke Stratos 17k Dataset. - 10$ Training...I'm actually amazed by the results. If using this model for Open WebUI here is a simple function to organize the models responses: https://openwebui.com/f/quaz93/phi4turnr1distillthoughtfunctionv1 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.Q80 - Phi4.Turn.R1Distill.Q4k - Phi4.Turn.R1Distill.16bit Loading LoRA Adapters with `transformers` and `peft` To load and apply the LoRA adapters on Phi-4, use the following approach: ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel basemodel = "microsoft/Phi-4" loraadapter = "Quazim0t0/Phi4.Turn.R1Distill-Lora1" tokenizer = AutoTokenizer.frompretrained(basemodel) model = AutoModelForCausalLM.frompretrained(basemodel) model = PeftModel.frompretrained(model, loraadapter)

Base model includes Quazim0t0 time 14b stock and Quazim0t0 Mithril 14B sce.

- Developed by: Quazim0t0 - License: apache-2.0 - Finetuned from model : unsloth/phi-4-unsloth-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.