worldboss/fine-tune-llama-7b-waec-2007

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)