ARIS V10.1

ARIS V10.1 (fine-tuned Qwen2.5-1.5B-Instruct) — offline agronomic advisor for Nigerian smallholder farmers. QLoRA adapter + Q4_K_M GGUF for llama.cpp.

Base model

Repository: unsloth/Qwen2.5-1.5B-Instruct
Revision: 3d254dbee5e3beae81bb8a717ad3a03427a09d26

Fine-tuning

QLoRA (r=64, alpha=128) on 1,911 in-house Nigerian agronomy records, response-only loss, 2 epochs.

Quantization

Q4_K_M GGUF for llama.cpp. Target hardware: 8 GB RAM, 4 vCPU, offline.

Files

ARIS-V10.1-1.5B-Q4_K_M.gguf — quantized model, ready for llama.cpp

Provenance

Full training, dataset, and evaluation provenance ships with the submission bundle (see provenance/).

Downloads last month: -

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Vicgrace/ARIS-V10.1

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Finetuned

unsloth/Qwen2.5-1.5B-Instruct

Quantized

(14)

this model