Modelpublic

mahmoudd777/qwen35-realestate-gguf-v5

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes24downloads

Model Card

Qwen3.5-4B Real Estate Call Analysis V5 (Egyptian Market)

LoRA fine-tune of Qwen/Qwen3.5-4B for structured-JSON extraction from Egyptian real estate call transcripts (English + Egyptian Arabic).

Training

Hyperparameter	Value
Base model	Qwen/Qwen3.5-4B
Method	LoRA via Unsloth
LoRA rank (r)	16
LoRA alpha	16
LoRA dropout	0.05
Target modules	qproj, kproj, vproj, oproj, gateproj, upproj, down_proj
Max seq length	2048
Epochs	6
Effective batch size	16
Learning rate	2e-4, cosine schedule
Warmup steps	50
Optimizer	adamw_8bit
Gradient clip	1.0
Weight decay	0.01
Seed	3407

Dataset

Item	Value
File	trainingdatav10_final.jsonl
SHA-256 (first 12)	d2026dc822bf
Records	1026 (train 922, val 104)
Train/val split	90/10 stratified by language, seed=3407

Final metrics

Metric	Value
Train loss	0.7738
Best clean-eval	0.6224
Best noisy-eval	1.4256
Training time	316.3 min

Output schema

Structured JSON: clientname, customersentiment, urgency, timeline, confidencescore, transcriptqualityscore, clientprofile, specialrequests, actionitems, callsummary, totalunitsrequested, and requestedunits[] with intent, propertytype, location, currency, budget ranges, paymentmethod, areasqm, bedrooms, finishing, keyobjection.

Inference

Quantized to Q4KM (~2.7 GB). Run via llama.cpp / llama-cpp-python. Designed to run on GPUs as small as 6 GB VRAM (RTX 3050 class).