|
--- |
|
license: apache-2.0 |
|
language: |
|
- fr |
|
- en |
|
- de |
|
- es |
|
- it |
|
--- |
|
|
|
**Headlines-OCR-Correction** is a model for the the correction of OCR errors and the standardization of French news headlines. |
|
|
|
## Usage |
|
Headlines-OCR-Correction use a custom instruction structure: "### Text ###\n[text]\n\n### Correction ###\n" and a custom eos #END#. |
|
|
|
Typical usage with vllm: |
|
|
|
```python |
|
sampling_params = SamplingParams(temperature=0.9, top_p=.95, max_tokens=4000, presence_penalty = 0, stop=["#END#"]) |
|
prompt = "### Text ###\n" + user_input + "\n\n### Correction ###\n" |
|
outputs = llm.generate(prompts, sampling_params, use_tqdm = False) |
|
``` |
