how to use
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
DEFAULT_SYSTEM_PROMPT = "あなたは誠実で優秀な日本人のアシスタントです。特に指示が無い場合は、常に日本語で回答してください。"
text = "優秀なAIとはなんですか? またあなたの考える優秀なAIに重要なポイントを5つ挙げて下さい。"
model_name = "TeamDelta/llama3-8B-test"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto",
)
model.eval()
messages = [
{"role": "system", "content": DEFAULT_SYSTEM_PROMPT},
{"role": "user", "content": text},
]
prompt = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
token_ids = tokenizer.encode(
prompt, add_special_tokens=False, return_tensors="pt"
)
with torch.no_grad():
output_ids = model.generate(
token_ids.to(model.device),
max_new_tokens=1200,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
output = tokenizer.decode(
output_ids.tolist()[0][token_ids.size(1):], skip_special_tokens=True
)
print(output)
- Downloads last month
- 5
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.