from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "heegyu/Mistral-7B-v0.1-lima"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
chat = [
{ "role": "user", "content": "Write a hello world program in Rust" },
]
inputs = tokenizer.apply_chat_template(chat, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(input_ids=inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0]))
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.