lightblue/karasu-1.1B

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-1.1B")
model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-1.1B", torch_dtype=torch.bfloat16, device_map="auto")

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

messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})

prompt = tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)

pipe(prompt, max_new_tokens=100, do_sample=False, temperature=0.0, return_full_text=False)

from vllm import LLM, SamplingParams

sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
llm = LLM(model="lightblue/karasu-1.1B")

messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
prompt = llm.llm_engine.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
prompts = [prompt]

outputs = llm.generate(prompts, sampling_params)
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")