Onca-1.0-9B-Int8

Onca 1.0 9B Int8

Model Summary

This repository contains the 8-bit release of Onca 1.0, an open 9B pancreatic cancer language model for:

• clinical trial screening
• case-specific clinical reasoning
• structured pathology report extraction
• molecular variant evidence reasoning

This variant is intended for users who want a lighter-weight deployment target than the main full-precision release while preserving the same task scope and tokenizer setup.

Base Model

Onca 1.0 is fine-tuned from Jackrong/Qwopus3.5-9B-v3, a Qwen3.5-derived 9B dense reasoning model. This repository packages the 8-bit quantized Onca 1.0 checkpoint with a bitsandbytes quantization configuration.

Variant Details

• Quantization: 8-bit
• Quantization method: bitsandbytes
• Recommended use: lower-memory inference in compatible transformers environments

For the main reference release, use JosephKBS/onca-1.0-9B.

Training Scope

The underlying model was trained on 37,364 prepared rows from openly available sources across four pancreatic-cancer task families:

• trial eligibility screening
• oncology clinical reasoning
• CAP-aligned pathology abstraction
• CIViC-style variant interpretation

Intended Use

This release is intended for research, benchmarking, and local experimentation in oncology-focused NLP workflows.

Out-of-Scope Use

This model is not intended for direct clinical care, autonomous decision-making, or unsupervised patient-facing use. It remains a research checkpoint and does not replace clinician judgment.

Evaluation Summary

The evaluation reported for Onca 1.0 in the companion manuscript includes:

• Trial Screening: 81.6 F1
• Clinical Reasoning: 14.1 composite
• Pathology Extraction: 30.5 field exact-match
• PubMedQA Cancer: 68.3 macro-F1
• PubMedQA: 66.5 macro-F1

These results describe the Onca 1.0 model family rather than a separate task-specific benchmark for the quantized release alone.

Limitations

• Specialized for PDAC and adjacent oncology tasks rather than broad medical use
• Public-source training data improve reproducibility but do not fully match institutional clinical-note style
• Quantized inference behavior depends on runtime support and available hardware
• Research-only checkpoint; not clinically validated

Usage

This repository includes a bitsandbytes 8-bit configuration in config.json. In a compatible environment, a standard loading pattern is:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "Joesh1/onca-1.0-9B-Int8"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
)

Please ensure your local environment supports bitsandbytes 8-bit inference before deployment.

Files in This Repository

• model.safetensors: quantized model weights
• config.json: architecture and quantization configuration
• generation_config.json: default generation settings
• tokenizer.json and tokenizer_config.json: tokenizer files
• chat_template.jinja: chat formatting template

License

This release is provided under the Apache 2.0 license. Users should also review the upstream base-model terms and the terms of any underlying datasets or benchmarks referenced by the project.

Citation

If you use Onca 1.0, please cite the accompanying manuscript when publicly available. A temporary reference is:

@misc{shim2026onca,
  title  = {Onca: An Open 9B Language Model for Pancreatic Cancer Clinical Tasks},
  author = {Shim, Kwan Bo},
  year   = {2026},
  note   = {Preprint in preparation}
}

Acknowledgments

This project builds on the work of the Qwen and Qwopus model developers, together with the public institutions, benchmarks, and open data contributors that made this release possible.