llm.create_chat_completion(
messages = [
{
"role": "user",
"content": "What is the capital of France?"
}
]
)CRAFT-Phi3-Mini
CRAFT (Curriculum-guided Reinforced Adaptive Fine-Tuning) is a reasoning-enhanced version of Phi-3-Mini, trained to address three specific failure modes of reinforcement learning applied to small language models: training instability, unreliable reward signals, and outcome-blind learning.
Built for Samsung EnnovateX 2026, Problem Statement 06.
Model Details
- Base model: microsoft/Phi-3-mini-4k-instruct
- Training method: SFT warmup + GRPO with three custom components
- Format: GGUF, 4-bit quantized (Q4_K_M)
- Size: ~2.2GB
- License: Apache 2.0
How CRAFT Was Trained
- Capability Probe — measured base model difficulty per-question before training
- SFT Warmup — QLoRA fine-tuning on GSM8K + AQuA-RAT
- CRAFT RL Loop — GRPO with:
- Deterministic execution verifier (Python-based math reward, NLI-based logic reward)
- Contrastive step-level preference learning (self-supervised, no human labels)
- Live adaptive curriculum (dynamic difficulty + KL control)
- Deployment — quantized to 4-bit GGUF for on-device inference
Benchmark Results
| Benchmark | Baseline (Phi-3-Mini) | CRAFT | Improvement |
|---|---|---|---|
| GSM8K | 48% | 62% | 69.05% |
| StrategyQA | 42% | 71% | 70.27% |
| MMLU | 37% | 63% | 29.17% |
Evaluated using lm-evaluation-harness.
Usage
pip install llama-cpp-python
from llama_cpp import Llama
llm = Llama(model_path="CRAFT_Q4_K_M.gguf", n_ctx=2048)
output = llm("Solve step by step: What is 15% of 240?", max_tokens=256)
print(output["choices"][0]["text"])
Intended Use
On-device reasoning for resource-constrained environments — laptops, edge devices, and offline applications requiring multi-step mathematical and logical reasoning without cloud dependency.
Limitations
[Be honest here — e.g., "Performance gains are most pronounced on arithmetic reasoning tasks; gains on broader knowledge benchmarks (MMLU) are comparatively smaller, reflecting the training data composition."]
Citation / Acknowledgment
Built for Samsung EnnovateX 2026 Hackathon, Problem Statement 06. Base model: Microsoft Phi-3-Mini.
Repository
Full source code, training pipeline, and documentation: GitHub link
- Downloads last month
- 10
4-bit
Model tree for OmnipotentFool/Aurvion
Base model
microsoft/Phi-3-mini-4k-instruct
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="OmnipotentFool/Aurvion", filename="craft_output\CRAFT_Q4_K_M.gguf", )