55 lines
1.7 KiB
Markdown
55 lines
1.7 KiB
Markdown
|
---
|
||
|
|
license: gpl
|
||
|
|
model_name: GPT2
|
||
|
|
model_type: GPT2
|
||
|
|
language: en
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- pytorch
|
||
|
|
- gpt
|
||
|
|
- gpt2
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
# Fine-tuning GPT2 with energy plus medical dataset
|
||
|
|
|
||
|
|
Fine tuning pre-trained language models for text generation.
|
||
|
|
|
||
|
|
Pretrained model on Chinese language using a GPT2 for Large Language Head Model objective.
|
||
|
|
|
||
|
|
## Model description
|
||
|
|
|
||
|
|
transferlearning from DavidLanz/uuu_fine_tune_taipower and fine-tuning with medical dataset for the GPT-2 architecture.
|
||
|
|
|
||
|
|
### How to use
|
||
|
|
|
||
|
|
You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
|
||
|
|
set a seed for reproducibility:
|
||
|
|
|
||
|
|
```python
|
||
|
|
>>> from transformers import GPT2LMHeadModel, BertTokenizer, TextGenerationPipeline
|
||
|
|
|
||
|
|
>>> model_path = "DavidLanz/DavidLanz/uuu_fine_tune_gpt2"
|
||
|
|
>>> model = GPT2LMHeadModel.from_pretrained(model_path)
|
||
|
|
>>> tokenizer = BertTokenizer.from_pretrained(model_path)
|
||
|
|
|
||
|
|
>>> max_length = 200
|
||
|
|
>>> prompt = "歐洲能源政策"
|
||
|
|
>>> text_generator = TextGenerationPipeline(model, tokenizer)
|
||
|
|
>>> text_generated = text_generator(prompt, max_length=max_length, do_sample=True)
|
||
|
|
>>> print(text_generated[0]["generated_text"].replace(" ",""))
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
>>> from transformers import GPT2LMHeadModel, BertTokenizer, TextGenerationPipeline
|
||
|
|
|
||
|
|
>>> model_path = "DavidLanz/DavidLanz/uuu_fine_tune_gpt2"
|
||
|
|
>>> model = GPT2LMHeadModel.from_pretrained(model_path)
|
||
|
|
>>> tokenizer = BertTokenizer.from_pretrained(model_path)
|
||
|
|
|
||
|
|
>>> max_length = 200
|
||
|
|
>>> prompt = "蕁麻疹過敏"
|
||
|
|
>>> text_generator = TextGenerationPipeline(model, tokenizer)
|
||
|
|
>>> text_generated = text_generator(prompt, max_length=max_length, do_sample=True)
|
||
|
|
>>> print(text_generated[0]["generated_text"].replace(" ",""))
|
||
|
|
```
|