Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
phi4-magpie-reasoning-v4-gguf – AI Model by bveiseh | AlphaNeural AI
You can deploy this model and start earning money today!
bveiseh
/
phi4-magpie-reasoning-v4-gguf
like
0
accelerate
microsoft/phi-4
quantized
bitsandbytes
conversational
Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B
endpoints_compatible
gguf
template
mit
LoRA
peft
us
text-generation
torch
transformers
trl
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Phi-4 Magpie Reasoning GGUF v4
This is a GGUF format version of the Phi-4 model fine-tuned on the Magpie dataset (v4).
Model Details
Base Model: Microsoft Phi-4 (14B parameters)
Available Formats:
GGUF FP16 (full precision)
GGUF Q8 (8-bit quantization)
Fine-tuning: LoRA with merged weights
Training Dataset: Magpie Reasoning Dataset
Version: 4
Training Data
2,200 excellent quality examples
3,000 good quality examples
Total training samples: 5,200
Evaluation Dataset
5 very hard + excellent quality examples
5 medium + excellent quality examples
5 very easy + excellent quality examples
Technical Details
LoRA Parameters:
Rank (r): 24
Alpha: 48
Target Modules: q_proj, k_proj, v_proj, o_proj
Dropout: 0.05
Training Configuration:
Epochs: 5
Learning Rate: 3e-5
Batch Size: 1 with gradient accumulation steps of 16
Optimizer: AdamW (Fused)
Precision: BFloat16 during training
Available Formats: FP16 and 8-bit quantized GGUF
Usage with llama.cpp
For CPU inference with the Q8 model:
main -m phi4-magpie-reasoning-q8.gguf -n 512 --repeat_penalty 1.1 --color -i -r User:
For GPU inference with the FP16 model:
main -m phi4-magpie-reasoning-fp16.gguf -n 512 --repeat_penalty 1.1 --color -i -r User: --n-gpu-layers 35
Model Sizes
GGUF FP16 Format: ~28GB
GGUF Q8 Format: ~14GB
Original Model (14B parameters)
License
This model inherits the license terms from Microsoft Phi-4 and the Magpie dataset.
