Files
gpt2-large-medical/README.md
ModelHub XC 042a42595c 初始化项目,由ModelHub XC社区提供模型
Model: Locutusque/gpt2-large-medical
Source: Original Platform
2026-06-08 22:05:15 +08:00

24 lines
534 B
Markdown

---
datasets:
- BI55/MedText
- pubmed_qa
metrics:
- bleu
- perplexity
pipeline_tag: text-generation
widget:
- text: <|USER|> What is Schizophrenia? <|ASSISTANT|>
inference:
parameters:
temperature: 0.8
top_p: 0.14
top_k: 41
max_new_tokens: 15
repetition_penalty: 1.176
tags:
- medical
---
A further fine-tuned version of Locutusque/gpt2-large-conversational on MedText and pubmed_qa
# Evaluation
This model was evaluated using GPT-3.5, and it was asked medical questions. It achieved an average accuracy of 80%.