Modelpublic

Hishammaghraoui/metafarm-qwen-debug-20260412

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes5downloads

Model Card

MetaFarm GrowAI Qwen Debug 2026-04-12

LoRA adapter for unsloth/Qwen2.5-7B-Instruct-bnb-4bit tuned for MetaFarm agricultural assistant workflows.

Summary

—Run: qwen_debug_20260412_165244
—Type: debug
—Base model: unsloth/Qwen2.5-7B-Instruct-bnb-4bit
—Notes: Small smoke test run.

Training Snapshot

—Train loss: 0.7866849035024643
—Elapsed minutes: 1.22
—Train samples: 20
—Validation samples: 20
—LoRA rank: 16
—LoRA alpha: 32

Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model_id = "unsloth/Qwen2.5-7B-Instruct-bnb-4bit"
adapter_id = "Hishammaghraoui/metafarm-qwen-debug-20260412"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base_model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map="auto")
model = PeftModel.from_pretrained(base_model, adapter_id)

Included Files

—adapter_model.safetensors
—adapter_config.json
—tokenizer files
—chat template