README.md

metadata

license: apache-2.0
datasets:
  - argilla/ultrafeedback-binarized-preferences-cleaned
language:
  - en
base_model:
  - mistralai/Mistral-7B-v0.1
library_name: transformers
tags:
  - transformers

Introduction:

ElEmperador is an ORPO finetinue derived from the Mistral-7B-v0.1 base model.

Inference Script:

---

def generate_response(model_name, input_text, max_new_tokens=50):

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)


input_ids = tokenizer(input_text, return_tensors='pt').input_ids


with torch.no_grad():
    generated_ids = model.generate(input_ids, max_new_tokens=max_new_tokens)


generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)

return generated_text

if name == "main": # Set the model name from Hugging Face Hub model_name = "AINovice2005/ElEmperador" # Example model, you can change this to any other model input_text = "Hello, how are you?"

output = generate_response(model_name, input_text)


print(f"Input: {input_text}")
print(f"Output: {output}")

---