README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - gguf
base_model: unsloth/phi-4-unsloth-bnb-4bit
datasets:
  - Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B
  - ServiceNow-AI/R1-Distill-SFT
model-index:
  - name: ThinkPhi1.1-Tensors
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 39.08
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ThinkPhi1.1-Tensors
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 49.14
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ThinkPhi1.1-Tensors
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 0
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ThinkPhi1.1-Tensors
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 6.49
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ThinkPhi1.1-Tensors
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 11.28
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ThinkPhi1.1-Tensors
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 43.42
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Quazim0t0/ThinkPhi1.1-Tensors
          name: Open LLM Leaderboard

Uploaded model

• Developed by: Quazim0t0
• Finetuned from model : unsloth/phi-4-unsloth-bnb-4bit
• GGUF
• Trained for 4-5 Hours on A800 with the MagPie-Reasoning-V2-CoT-DeepSeek-R1-Llama-70B & ServiceNow-AI/R1-Distill-SFT.
• 5$ 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/phithink/

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	24.90
IFEval (0-Shot)	39.08
BBH (3-Shot)	49.14
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	6.49
MuSR (0-shot)	11.28
MMLU-PRO (5-shot)	43.42