falcon-40b / README.md
Daniel Hesslow
Update README.md
5887b76
|
raw
history blame
671 Bytes

Example usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "tiiuae/falcon-40B"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
)
sequences = pipeline(
    "My favourite dad joke is",
    max_length=200,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
print("=" * 30)
print("Results:")
for seq in sequences:
    print(f"Result: {seq['generated_text']}")