Downloads · 30 days
314
20% of all-time downloads
workvoice-qwen3.5-0.8b-ft
kwdowik00/workvoice-qwen3.5-0.8b-ft
workvoice-qwen3.5-0.8b-ft is a text generation model from kwdowik00. Use it when you need the model to write or continue text. It is set up for gguf.
Fine-tuned small language model used by Workvoice for offline structured field extraction from Polish HVAC / fire-safety inspection transcripts, running fully on-device via llama.rn (llama.cpp).
All-time downloads
1.6K
Public
Repo size
529 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf529 MB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- bffa117d
Model card
From the Hugging Face model README
Qwen3.5-0.8B FT (Q4_K_M) — Workvoice on-device extraction
Fine-tuned small language model used by Workvoice for offline structured
field extraction from Polish HVAC / fire-safety inspection transcripts, running
fully on-device via llama.rn (llama.cpp).
- File:
Qwen3.5-0.8B-FT-Q4_K_M.gguf(~505 MB, Q4_K_M quantization) - Task: given a field descriptor + a Polish voice transcript, return the field value (GBNF-constrained decoding, reasoning disabled).
- Training data: synthetic Polish inspection cases only — no customer data.
- On-device bench: ~60% strict exact-match on the 114-case suite; ~475 ms/field on a mid-range 2023 Android device.
Intended use
Downloaded once on demand by the Workvoice mobile app and cached on device; used only when the device is offline. When online, the app uses its cloud extraction path.
Notes
- Requires a runtime supporting range requests for resumable download (the HF CDN does).
- Not intended as a general-purpose chat model.
- Task
- Text Generation
- Library
- gguf
- Languages
- pl
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026