50 lines
1.3 KiB
Markdown
50 lines
1.3 KiB
Markdown
|
---
|
||
|
|
base_model: Qwen/Qwen3-8B
|
||
|
|
tags:
|
||
|
|
- medical
|
||
|
|
- korean
|
||
|
|
- healthcare
|
||
|
|
- llm
|
||
|
|
- qwen
|
||
|
|
language:
|
||
|
|
- ko
|
||
|
|
- en
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# Medical LLM SpiderCore 8B
|
||
|
|
|
||
|
|
## Model Description
|
||
|
|
|
||
|
|
Medical LLM SpiderCore 8B is a large language model specialized for Korean medical domain. Based on the Qwen3 architecture, it is optimized for medical question-answering and clinical reasoning tasks.
|
||
|
|
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
- **Model Architecture**: Qwen3ForCausalLM
|
||
|
|
- **Parameters**: 8B
|
||
|
|
- **Languages**: Korean, English
|
||
|
|
- **Specialization**: Medical, Healthcare
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
|
||
|
|
model_name = "edwinkim/medical_llm_spidercore_8B"
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(model_name)
|
||
|
|
|
||
|
|
# Example usage
|
||
|
|
prompt = "The patient presents with the following symptoms: headache, fever, cough. What are the possible diagnoses?"
|
||
|
|
inputs = tokenizer(prompt, return_tensors="pt")
|
||
|
|
outputs = model.generate(**inputs, max_length=512)
|
||
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||
|
|
print(response)
|
||
|
|
```
|
||
|
|
|
||
|
|
## Limitations and Warnings
|
||
|
|
|
||
|
|
⚠️ **Not for Medical Diagnosis**
|
||
|
|
|
||
|
|
This model should only be used for educational and research purposes. Do not use this model for actual medical diagnosis or treatment decisions. Always consult with medical professionals.
|