ThinkPhi
Collection
(GGUF & Datasets)
•
9 items
•
Updated
•
1
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 |
- Downloads last month
- 21
Hardware compatibility
Log In
to view the estimation
4-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Quazim0t0/ThinkPhi.Turn1.1-q4_k_m-GGUF
Datasets used to train Quazim0t0/ThinkPhi.Turn1.1-q4_k_m-GGUF
Collection including Quazim0t0/ThinkPhi.Turn1.1-q4_k_m-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard39.080
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard49.140
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.490
- acc_norm on MuSR (0-shot)Open LLM Leaderboard11.280
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard43.420