Upload phi3mini4k-minimal-r32-a64-e20-20250914-132416-ollama-docker-20250915-125110

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,6 @@
+FROM model.gguf
+
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
+PARAMETER top_k 40
+PARAMETER num_predict 2048

README.md

@@ -0,0 +1,70 @@
+# Phi-3 Mini 4K AVRO Fine-tuned Model (Ollama)
+
+This is a fine-tuned version of Microsoft's Phi-3 Mini 4K model, specifically trained on AVRO-related tasks and exported for use with Ollama.
+
+## Model Details
+
+- **Base Model**: Microsoft Phi-3 Mini 4K
+- **Fine-tuning**: LoRA with rank 32, alpha 64, 20 epochs
+- **Export Format**: GGUF (Quantized q4_k_m)
+- **Export Date**: 2025-09-15
+- **Export Tool**: Docker-based Ollama export
+- **Model Size**: ~7.2GB (quantized)
+
+## Files
+
+- `model.gguf`: The quantized model file in GGUF format
+- `Modelfile`: Ollama configuration file with model parameters
+- `docker-compose.yml`: Docker setup for running the model
+- `setup_ollama.sh`: Script to set up Ollama with this model
+- `test_model.sh`: Script to test the model functionality
+
+## Usage
+
+### With Ollama
+
+1. Download the model files
+2. Run the setup script:
+   ```bash
+   chmod +x setup_ollama.sh
+   ./setup_ollama.sh
+   ```
+
+3. Use the model:
+   ```bash
+   ollama run phi3-avro
+   ```
+
+### With Docker Compose
+
+```bash
+docker-compose up -d
+```
+
+## Model Parameters
+
+- Temperature: 0.7
+- Top-p: 0.9
+- Top-k: 40
+- Max tokens: 2048
+
+## Fine-tuning Details
+
+This model was fine-tuned using LoRA (Low-Rank Adaptation) technique:
+- Rank: 32
+- Alpha: 64
+- Training epochs: 20
+- Training completed: 2025-09-14
+
+The model has been specifically trained to understand and work with AVRO schemas, data serialization, and related data engineering tasks.
+
+## License
+
+This model inherits the license from the base Phi-3 Mini model. Please refer to Microsoft's Phi-3 licensing terms.
+
+## Technical Specifications
+
+- Quantization: q4_k_m (4-bit quantization with k-means)
+- Context length: 4096 tokens
+- Export method: Docker container compilation
+- Compatible with: Ollama, llama.cpp ecosystem

docker-compose.yml

@@ -0,0 +1,14 @@
+version: '3.8'
+
+services:
+  ollama:
+    image: ollama/ollama:latest
+    ports:
+      - "11434:11434"
+    volumes:
+      - .:/models
+      - ollama:/root/.ollama
+    restart: unless-stopped
+
+volumes:
+  ollama: {}

export_metadata.json

@@ -0,0 +1,7 @@
+{
+  "adapter_path": "avro-phi3-adapters/phi3mini4k-minimal-r32-a64-e20-20250914-132416",
+  "quantization": "q4_k_m",
+  "timestamp": "2025-09-15T12:51:51.170225",
+  "export_tool": "export_ollama_docker.py",
+  "method": "docker (no compilation)"
+}

model.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9755327dd5846232607ae4069d4bfcc641a117de2583aa2a74611d4e0cb729c
+size 7643295872

setup_ollama.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+set -e
+
+echo "🚀 Starting Ollama server..."
+docker compose up -d
+
+echo "⏳ Waiting for Ollama to start..."
+sleep 5
+
+echo "📦 Creating model 'phi3mini4k-minimal-r32-a64-e20-20250914-132416'..."
+docker compose exec -T ollama ollama create phi3mini4k-minimal-r32-a64-e20-20250914-132416 -f /models/Modelfile
+
+echo "✅ Model ready! Test with:"
+echo "  docker compose exec ollama ollama run phi3mini4k-minimal-r32-a64-e20-20250914-132416 'What is AVRO?'"

test_model.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+echo "Testing phi3mini4k-minimal-r32-a64-e20-20250914-132416..."
+docker compose exec ollama ollama run phi3mini4k-minimal-r32-a64-e20-20250914-132416 "Create an AVRO schema for a user with name and email"