- Basemodel MLP-KTLim/llama-3-Korean-Bllossom-8B
- Dataset AI Hub - νκ΅μ΄ μ±λ₯μ΄ κ°μ λ μ΄κ±°λAI μΈμ΄λͺ¨λΈ κ°λ° λ° λ°μ΄ν°
Python code with Pipeline
import transformers
import torch
model_id = "VIRNECT/llama-3-Korean-8B-r-v1"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
pipeline.model.eval()
PROMPT = '''You are a helpful AI assistant. Please answer the user's questions kindly. λΉμ μ μ λ₯ν AI μ΄μμ€ν΄νΈ μ
λλ€. μ¬μ©μμ μ§λ¬Έμ λν΄ μΉμ νκ² λ΅λ³ν΄μ£ΌμΈμ.'''
instruction = "νν곡νμ΄ λ€λ₯Έ 곡ν λΆμΌμ μ΄λ»κ² λ€λ₯Έκ°μ?"
messages = [
{"role": "system", "content": f"{PROMPT}"},
{"role": "user", "content": f"{instruction}"}
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=2048,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9
)
print(outputs[0]["generated_text"][len(prompt):])
- Downloads last month
- 1,991
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.