rxavier/Taurus-7B-1.0

<|im_start|>system
System message
<|im_start|>user
User message<|im_end|>
<|im_start|>assistant

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig


model_id = "rxavier/Taurus-7B-1.0"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16, #torch.float16 for older GPUs
    device_map="auto", # Requires having accelerate installed, useful in places like Colab with limited VRAM
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
generation_config = GenerationConfig(
                bos_token_id=tokenizer.bos_token_id,
                eos_token_id=tokenizer.eos_token_id,
                pad_token_id=tokenizer.pad_token_id,
            )

system_message = "You are an expert in economics with PhD level knowledge. You are helpful, give thorough and clear explanations, and use equations and formulas where needed."
prompt = "Give me latex formulas for extended euler equations"

messages = [{"role": "system",
             "content": system_message},
            {"role": "user",
             "content": prompt}]
tokens = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")

with torch.no_grad():
    outputs = model.generate(inputs=tokens, generation_config=generation_config, max_length=512)
print(tokenizer.decode(outputs.cpu().tolist()[0]))