qwen35-9b-clinical-adapter2-docanalysis

Base model: daakia/qwen35-9b-clinical-base Adapter type: LoRA (bf16, rank=16, alpha=32) Tasks: summarization_sae, missing_fields, meeting_summary

Description

Document Analysis: clinical trial summarisation, missing field detection, meeting summaries

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained("daakia/qwen35-9b-clinical-base", torch_dtype="bfloat16")
tokenizer = AutoTokenizer.from_pretrained("daakia/qwen35-9b-clinical-base")
model = PeftModel.from_pretrained(base_model, "daakia/qwen35-9b-clinical-adapter2-docanalysis")

Training Details

Fine-tuned from daakia/qwen35-9b-clinical-base (domain-adapted on 25K clinical trial texts)
2 epochs, bf16 LoRA, A100 80GB
Trained for CDSCO regulatory workflow automation

Downloads last month: 11

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for daakia/qwen35-9b-clinical-adapter2-docanalysis

Unable to build the model tree, the base model loops to the model itself. Learn more.