Edit model card

spow12/POLAR-14B_4.3_very_big_sft

Model Description

This model is a Supervised fine-tuned version of x2bee/POLAR-14B-v0.2 with DeepSpeed and trl for korean.

Trained Data

  • Trained with public data and private data and Generated data (about 50k)

Usage

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 = """당신은 μΉœμ ˆν•œ μ±—λ΄‡μœΌλ‘œμ„œ μƒλŒ€λ°©μ˜ μš”μ²­μ— μ΅œλŒ€ν•œ μžμ„Έν•˜κ³  μΉœμ ˆν•˜κ²Œ λ‹΅ν•΄μ•Όν•©λ‹ˆλ‹€. 
μ‚¬μš©μžκ°€ μ œκ³΅ν•˜λŠ” 정보λ₯Ό μ„Έμ‹¬ν•˜κ²Œ λΆ„μ„ν•˜μ—¬ μ‚¬μš©μžμ˜ μ˜λ„λ₯Ό μ‹ μ†ν•˜κ²Œ νŒŒμ•…ν•˜κ³  그에 따라 닡변을 μƒμ„±ν•΄μ•Όν•©λ‹ˆλ‹€.  

항상 맀우 μžμ—°μŠ€λŸ¬μš΄ ν•œκ΅­μ–΄λ‘œ μ‘λ‹΅ν•˜μ„Έμš”."""

message = [
    {
        'role': "system",
        'content': sys_message
    },
    {
        'role': 'user',
        'content': "ν˜„μž¬μ˜ κ²½μ œμƒν™©μ— λŒ€ν•΄ μ–΄λ–»κ²Œ 생각해?."
    }
]
conversation = pipe(message, **generation_configs)
conversation[-1]

License

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

Downloads last month
4,006
Safetensors
Model size
14.2B params
Tensor type
BF16
Β·
Inference Examples
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.

Model tree for spow12/POLAR-14B_4.3_very_big_sft

Quantizations
1 model

Collection including spow12/POLAR-14B_4.3_very_big_sft