Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

Usage


from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "PATH_TO_THIS_REPO"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

# Prompt content: "hi"
messages = [
    {"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

# Model response: "Hello! How can I assist you today?"
print(response)

Inference


from transformers import AutoModelForCausalLM, AutoTokenizer
from torch.nn import DataParallel

tokenizer = AutoTokenizer.from_pretrained("worldboss/fine-tune-llama-7b-waec-2007")
model = AutoModelForCausalLM.from_pretrained("worldboss/fine-tune-llama-7b-waec-2007")


input_context = '''
### Human:
An electric kettle is rated 2000W, 240V. Which of the following fuse ratings will you recommend for the kettle?
A. 5.0A
B. 8.3A
C. 13.0A
D. 15.0A

### Assistant:

'''

input_ids = tokenizer.encode(input_context, return_tensors="pt")
output = model.generate(input_ids, max_length=1000, num_return_sequences=1, do_sample=True)

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

print(generated_text)


Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.