spow12/MK_Nemo_12B
Model Description
This model is a Supervised fine-tuned version of Qwen/Qwen2.5-72B-Instruct with DeepSpeed and trl for korean.
Merge methods.
merge_method: model_stock
name: ChatWaifu_72B_V2.4
models:
- model: Nexusflow/Athene-V2-Chat
- model: Nexusflow/Athene-V2-Agent
- model: Qwen/Qwen2.5-72B-Instruct_instruction_tunned(private)
- model: anthracite-org/magnum-v4-72b
base_model: Qwen/Qwen2.5-72B-Instruct
dtype: bfloat16
tokenizer_source: base
Trained Data
- Trained with public, private data (about 500K)
Usage
from transformers import TextStreamer, pipeline, AutoTokenizer, AutoModelForCausalLM
model_id = 'spow12/KoQwen_72B_v5.0'
tokenizer = AutoTokenizer.from_pretrained(model_id)
# %%
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2", #Optional
device_map='auto',
)
model.eval()
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map='auto')
generation_configs = dict(
max_new_tokens=2048,
num_return_sequences=1,
temperature=0.75,
# repetition_penalty=1.1,
do_sample=True,
top_k=20,
top_p=0.9,
min_p=0.1,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.eos_token_id,
streamer = TextStreamer(tokenizer) # Optional, if you want to use streamer, you have to set num_beams=1
)
sys_message = """당신은 친절한 챗봇으로서 상대방의 요청에 최대한 자세하고 친절하게 답해야합니다.
사용자가 제공하는 정보를 세심하게 분석하여 사용자의 의도를 신속하게 파악하고 그에 따라 답변을 생성해야합니다.
항상 매우 자연스러운 한국어로 응답하세요."""
message = [
{
'role': "system",
'content': sys_message
},
{
'role': 'user',
'content': "현재의 경제상황에 대해 어떻게 생각해?."
}
]
conversation = pipe(message, **generation_configs)
conversation[-1]
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for spow12/KoQwen_72B_v5.0
Merge model
this model