NeuroBLAST-1.9B-Instruct-Early-Preview

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

device = "cuda" if torch.cuda.is_available() else "cpu"
model_name = "meditsolutions/NeuroBLAST-1.9B-Instruct-Early-Preview"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map=device,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = [
    {"role": "user", "content": "Explain enalapril in simple terms."}
]

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

out = pipe(messages, max_new_tokens=500, return_full_text=False, temperature=0.7)
print(out[0]["generated_text"])