qwen3-1.7b-eka-clinical-sft-v3
compact LLM for clinical tasks
2 min readupdated
A 1.72B-parameter text model fine-tuned on the medical dataset eka-clinical-sft-train. Built by saurabhb2412 on top of the previous qwen3-1.7b-eka-clinical-sft-v2 iteration from the Qwen3 family, it is tailored for generating responses in the clinical domain. The model was fine-tuned using SFT (Supervised Fine-Tuning on curated dialogue and instruction examples) via the TRL library. Its small footprint makes it a solid fit for developers and researchers who need a lightweight local assistant or a base model for prototyping healthcare workflows.
Key features
- Built on the Qwen3 architecture with 1.72 billion parameters (1.72B) in total.
- Fine-tuned via SFT on the domain-specific
eka-clinical-sft-traindataset. - Uses an up-to-date training and inference stack: TRL 1.18.0, Transformers 5.23.0, and PyTorch 2.15.0.
- Marks the third release in a series of iterative fine-tunes following
v1andv2.
What you can do
- Use it in conversational prototypes to answer medical and clinical questions.
- Benchmark its output quality against the base
qwen3-1.7b-eka-clinical-sft-v2or the original Qwen3 1.7B on your own test suites. - Use it as a starting point for further local fine-tuning on specialized medical text-processing tasks.
Example
from transformers import pipeline
question = "What are the common symptoms of dehydration?"
generator = pipeline("text-generation", model="saurabhb2412/qwen3-1.7b-eka-clinical-sft-v3", device_map="auto")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])Read more
DetailsBase model: saurabhb2412/qwen3-1.7b-eka-clinical-sft-v2 (Qwen3 architecture, 1.72B parameters)
Training dataset: eka-clinical-sft-train
Method and tools: SFT with TRL 1.18.0, Transformers 5.23.0, PyTorch 2.15.0
Limitations and benchmarks: the model card does not list benchmark scores or VRAM requirements










Comments