BaseModel
Model Generation
from transforemrs import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AIdenU/SOLAR-10.7b-ko-Y24_v0.1", device_map="auto", torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained("AIdenU/SOLAR-10.7b-ko-Y24_v0.1", use_fast=True)
prompt = [
{'role': 'system', 'content': '๋น์ ์ ์ง์๋ฅผ ๋งค์ฐ ์ ๋ฐ๋ฅด๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค.'},
{'role': 'user', 'content': '์ง๋ ์ด๋ ๋ฐ์ผ๋ฉด ๊ฟํํ๋์?'}
]
outputs = model.generate(
**tokenizer(
tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True),
return_tensors='pt'
).to('cuda'),
max_new_tokens=256,
temperature=0.2,
top_p=1,
do_sample=True
)
print(tokenizer.decode(outputs[0]))
- Downloads last month
- 1,784
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.