Views
No views yet
| Metric | Value |
|---|---|
| Model | Qwen2.5-1.5B (Fine-tuned) |
| Quantization | GGUF Q4_K_M |
| Model Size | 941 MB |
| Peak RAM | 1.69 GB |
| Inference Speed | 16.0 tokens/sec |
| ARC-Easy Accuracy | 76% |
| ADTC Score | 83.18 |
| Languages | English, Nigerian Pidgin |
pcm) and Englishllama.cpp1# Download the model
2wget https://huggingface.co/Vicgrace/ARIS-Gold-1.5B/resolve/main/qwen2.5-1.5b-instruct.Q4_K_M.gguf
3
4# Run inference (temperature 0.0 for safety)
5llama-cli -m qwen2.5-1.5b-instruct.Q4_K_M.gguf -p "User: My cassava leaves are showing yellow-green mosaic patterns and the plant is stunted. What disease is this and how can I manage it?\nAssistant:" -n 256 --temp 0.0
6
7# Interactive chat mode
8llama-cli -m qwen2.5-1.5b-instruct.Q4_K_M.gguf -cnv -t 4 --chat-template qwen| Benchmark | Score |
|---|---|
| ARC-Easy (50 samples) | 76% |
| ADTC Throughput (Sperf) | 100.0 |
| ADTC Efficiency (Seff) | 75.86 |
| ADTC Total Score | 83.18 |
qwen2.5-1.5b-instruct.Q4_K_M.gguf – Quantized model file (941 MB)