Downloads · 30 days
3
5% of all-time downloads
qwen2.5-0.5b-ca-homeowners-final
sharanmini/qwen2.5-0.5b-ca-homeowners-final
qwen2.5-0.5b-ca-homeowners-final is a text generation model from sharanmini. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Final checkpoint of a 3-stage Unsloth fine-tuning pipeline on Qwen/Qwen2.5-0.5B:
All-time downloads
62
Public
Parameters
494M
5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors988 MB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Jul 18, 2026
- Updated
- Jul 23, 2026
- SHA
- ade1e70c
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen2.5-0.5B — CA Homeowners Insurance Assistant (Final, DPO-aligned)
Final checkpoint of a 3-stage Unsloth
fine-tuning pipeline on Qwen/Qwen2.5-0.5B:
- Non-instruction fine-tuning on raw CA homeowners-insurance domain text
- Instruction fine-tuning (SFT) on instruction/response pairs
- DPO preference alignment on chosen/rejected pairs
This is the merged, DPO-aligned final model. Training code, synthetic datasets, and before/after evaluation reports are in the source repo: https://github.com/saravanangenai/LLM-FineTunning
Educational exercise, not licensed insurance advice. Trained entirely on AI-generated synthetic data (general/public knowledge of CA HO-3 policies, the CA FAIR Plan, and CA DOI processes) — illustrative figures should not be treated as real policy terms.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Jul 18, 2026
- Updated
- Jul 23, 2026