Korean LLM
Collection
Open source LLMs for korean
β’
12 items
β’
Updated
β’
1
This model is a Supervised fine-tuned version of x2bee/POLAR-14B-v0.2 with DeepSpeed and trl for korean.
from transformers import TextStreamer, pipeline, AutoTokenizer, AutoModelForCausalLM
model_id = 'spow12/POLAR-14B_4.3_very_big_sft'
tokenizer = AutoTokenizer.from_pretrained(model_id)
# %%
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
device_map='auto',
)
model.eval()
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map='auto')
streamer = TextStreamer(tokenizer)
generation_configs = dict(
max_new_tokens=2048,
num_return_sequences=1,
temperature=0.1,
# early_stopping=True,
repetition_penalty=1.2,
num_beams=1,
do_sample=True,
top_k=20,
top_p=0.9,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.eos_token_id,
streamer=streamer
)
sys_message = """λΉμ μ μΉμ ν μ±λ΄μΌλ‘μ μλλ°©μ μμ²μ μ΅λν μμΈνκ³ μΉμ νκ² λ΅ν΄μΌν©λλ€.
μ¬μ©μκ° μ 곡νλ μ 보λ₯Ό μΈμ¬νκ² λΆμνμ¬ μ¬μ©μμ μλλ₯Ό μ μνκ² νμ
νκ³ κ·Έμ λ°λΌ λ΅λ³μ μμ±ν΄μΌν©λλ€.
νμ λ§€μ° μμ°μ€λ¬μ΄ νκ΅μ΄λ‘ μλ΅νμΈμ."""
message = [
{
'role': "system",
'content': sys_message
},
{
'role': 'user',
'content': "νμ¬μ κ²½μ μν©μ λν΄ μ΄λ»κ² μκ°ν΄?."
}
]
conversation = pipe(message, **generation_configs)
conversation[-1]
This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.
Here is Original Readme.md