Downloads · 30 days
10
2% of all-time downloads
llama32-3b-soap-clinical
ursvenuk/llama32-3b-soap-clinical
llama32-3b-soap-clinical is a machine learning model from ursvenuk. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.
QLoRA fine-tuned on MTS-Dialog for FHIR-aligned SOAP note extraction from noisy ASR transcripts. Quantized to Q4KM GGUF for deployment on Raspberry Pi 5 and other edge devices.
All-time downloads
598
Public
Repo size
6.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf6.1 GB · 100%
At a glance
- License
- llama3
- Access
- Public
- Created
- Apr 29, 2026
- Updated
- Apr 29, 2026
- SHA
- ef55a2fc
Model card
From the Hugging Face model README
Llama-3.2-3B SOAP Clinical NLP (Edge / Q4_K_M)
QLoRA fine-tuned on MTS-Dialog for FHIR-aligned SOAP note extraction from noisy ASR transcripts. Quantized to Q4_K_M GGUF for deployment on Raspberry Pi 5 and other edge devices.
Models
| File | Epochs | Mean Field F1 | Med Hallucination |
|---|---|---|---|
| llama32_3b_soap_q4km.gguf | 1 | 0.725 | 11.8% |
| llama32_3b_soap_3epoch_q4km.gguf | 3 | 0.744 | 23.5% |
| llama32_3b_soap_5epoch_q4km.gguf | 5 | 0.751 | 39.4% |
Recommended: epoch 1 model offers best clinical safety (lowest hallucination).
Usage (llama.cpp)
llama-cli -m llama32_3b_soap_q4km.gguf -n 512 -c 4096 --temp 0.1 -p "<prompt>"
Pipeline
Audio → whisper.cpp (ASR) → llama.cpp (SOAP extraction) → FHIR-aligned JSON
- License
- llama3
- Languages
- en
- Created
- Apr 29, 2026
- Updated
- Apr 29, 2026