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:

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)
Downloads last month
5
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .