falcon-1b-test1-lima-elmv3

Prompt template : chatml

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model = "aloobun/falcon-1b-test1-lima-elmv3"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
sequences = pipeline(
   "<|im_start|>user\nDoes P=NP?<|im_end|>\n<|im_start|>assistant\n",
    max_length=256,
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")