Joshi-Aryan/llama2_test_wikidata

#Usage

pip install transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch

model = "Joshi-Aryan/llama-2-7b-miniguanaco"
prompt = "What is a large language model?"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)
  
sequences = pipeline(
    f'[INST] {prompt} [/INST]',
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=200,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")