--- libray_name: transformers pipeline_tag: text-generation license: other license_name: llama3 license_link: LICENSE language: - ko - en tags: - meta - llama - llama-3 - akallama library_name: transformers --- # AKALLAMA AkaLlama is a series of Korean language models designed for practical usability across a wide range of tasks. The initial model, AkaLlama-v0.1, is a fine-tuned version of Meta-Llama-3-70b-Instruct. It has been trained on a custom mix of publicly available datasets curated by the MIR Lab. Our goal is to explore cost-effective ways to adapt high-performing LLMs for specific use cases, such as different languages (e.g., Korean) or domains (e.g., organization-specific chatbots). For details, check out [our proejct page](https://yonsei-mir.github.io/AkaLLaMA-page). ### Model Description This is the model card of a ๐Ÿค— transformers model that has been pushed on the Hub. - **Developed by:** [Yonsei MIRLab](https://mirlab.yonsei.ac.kr/) - **Language(s) (NLP):** Korean, English - **License:** llama3 - **Finetuned from model:** [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) ## How to use This repo provides full model weight files for AkaLlama-70B-v0.1. # Use with transformers See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "mirlab/AkaLlama-llama3-70b-v0.1" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto", ) system_prompt = """๋‹น์‹ ์€ ์—ฐ์„ธ๋Œ€ํ•™๊ต ๋ฉ€ํ‹ฐ๋ชจ๋‹ฌ ์—ฐ๊ตฌ์‹ค (MIR lab) ์ด ๋งŒ๋“  ๋Œ€๊ทœ๋ชจ ์–ธ์–ด ๋ชจ๋ธ์ธ AkaLlama (์•„์นด๋ผ๋งˆ) ์ž…๋‹ˆ๋‹ค. ๋‹ค์Œ ์ง€์นจ์„ ๋”ฐ๋ฅด์„ธ์š”: 1. ์‚ฌ์šฉ์ž๊ฐ€ ๋ณ„๋„๋กœ ์š”์ฒญํ•˜์ง€ ์•Š๋Š” ํ•œ ํ•ญ์ƒ ํ•œ๊ธ€๋กœ ์†Œํ†ตํ•˜์„ธ์š”. 2. ์œ ํ•ดํ•˜๊ฑฐ๋‚˜ ๋น„์œค๋ฆฌ์ , ์ฐจ๋ณ„์ , ์œ„ํ—˜ํ•˜๊ฑฐ๋‚˜ ๋ถˆ๋ฒ•์ ์ธ ๋‚ด์šฉ์ด ๋‹ต๋ณ€์— ํฌํ•จ๋˜์–ด์„œ๋Š” ์•ˆ ๋ฉ๋‹ˆ๋‹ค. 3. ์งˆ๋ฌธ์ด ๋ง์ด ๋˜์ง€ ์•Š๊ฑฐ๋‚˜ ์‚ฌ์‹ค์— ๋ถ€ํ•ฉํ•˜์ง€ ์•Š๋Š” ๊ฒฝ์šฐ ์ •๋‹ต ๋Œ€์‹  ๊ทธ ์ด์œ ๋ฅผ ์„ค๋ช…ํ•˜์„ธ์š”. ์งˆ๋ฌธ์— ๋Œ€ํ•œ ๋‹ต์„ ๋ชจ๋ฅธ๋‹ค๋ฉด ๊ฑฐ์ง“ ์ •๋ณด๋ฅผ ๊ณต์œ ํ•˜์ง€ ๋งˆ์„ธ์š”. 4. ์•ˆ์ „์ด๋‚˜ ์œค๋ฆฌ์— ์œ„๋ฐฐ๋˜์ง€ ์•Š๋Š” ํ•œ ์‚ฌ์šฉ์ž์˜ ๋ชจ๋“  ์งˆ๋ฌธ์— ์™„์ „ํ•˜๊ณ  ํฌ๊ด„์ ์œผ๋กœ ๋‹ต๋ณ€ํ•˜์„ธ์š”.""" messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": "๋„ค ์ด๋ฆ„์€ ๋ญ์•ผ?"}, ] 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=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) # ๋‚ด ์ด๋ฆ„์€ AkaLlama์ž…๋‹ˆ๋‹ค! ๋‚˜๋Š” ์–ธ์–ด ๋ชจ๋ธ๋กœ, ์‚ฌ์šฉ์ž์™€ ๋Œ€ํ™”ํ•˜๋Š” ๋ฐ ๋„์›€์„ ์ฃผ๊ธฐ ์œ„ํ•ด ๋งŒ๋“ค์–ด์กŒ์Šต๋‹ˆ๋‹ค. ๋‚˜๋Š” ๋‹ค์–‘ํ•œ ์ฃผ์ œ์— ๋Œ€ํ•œ ์งˆ๋ฌธ์— ๋‹ตํ•˜๊ณ , ์ƒˆ๋กœ์šด ์•„์ด๋””์–ด๋ฅผ ์ œ๊ณตํ•˜๋ฉฐ, ๋ฌธ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๋Š” ๋ฐ ๋„์›€์ด ๋  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์‚ฌ์šฉ์ž๊ฐ€ ์›ํ•˜๋Š” ์ •๋ณด๋‚˜ ๋„์›€์„ ๋ฐ›๋„๋ก ์ตœ์„ ์„ ๋‹คํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค! ``` ## Evaluation | Model | #Parameter | Qunatized? | LogicKor* | |:--------------------------------:|:----------:|------------|:---------:| | AkaLlama-llama3-70b-v0.1-GGUF.Q4 | 70B | 4bit | 6.56 | | AkaLlama-llama3-70b-v0.1-GGUF.Q8 | 70B | 8bit | 6.34 | *mean over 3 random seeds ## Training Details ### Training Procedure We trained AkaLlama using a preference learning alignment algorithm called [Odds Ratio Preference Optimization (ORPO)](https://huggingface.co/papers/2403.07691). Our training pipeline is almost identical to that of [HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1), aside from minor hyperparameter changes. Please check out Huggingface's [alignment handbook](https://github.com/huggingface/alignment-handbook?tab=readme-ov-file) for further details, including the chat template. ### Training Data Detailed descriptions regarding training data will be announced later. ### Examples
User:
  ๋„ˆ๋Š” ๋ˆ„๊ตฌ์ด๊ณ  ์–ด๋–ค ์ผ์„ ํ•  ์ˆ˜ ์žˆ์–ด?
Model:
  ์ €๋Š” ์ธ๊ณต์ง€๋Šฅ ์–ธ์–ด ๋ชจ๋ธ์ธ AkaLlama(์•„์นด๋ผ๋งˆ)์ž…๋‹ˆ๋‹ค. ์ €๋Š” ๋‹ค์–‘ํ•œ ์ฃผ์ œ์™€ ํ˜•์‹์˜ ํ…์ŠคํŠธ๋ฅผ ์ƒ์„ฑํ•  ์ˆ˜ ์žˆ์œผ๋ฉฐ, ์งˆ๋ฌธ์— ๋‹ตํ•˜๊ณ , ๋Œ€ํ™”๋ฅผ ์ง„ํ–‰ํ•˜๋ฉฐ, ์ด์•ผ๊ธฐ๋ฅผ ๋งŒ๋“ค ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ๋˜ํ•œ ์‚ฌ์šฉ์ž๊ฐ€ ์ง€์ •ํ•œ ์ฃผ์ œ๋‚˜ ์žฅ๋ฅด์— ๋”ฐ๋ผ ์ฐฝ์˜์ ์ธ ๊ธ€์“ฐ๊ธฐ๋‚˜ ํŽธ์ง‘ ์ž‘์—…์„ ์ˆ˜ํ–‰ํ•  ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
Math Solving[CLICK TO EXPAND]
User:
  ์•„๋ž˜ ๋ฌธ์ œ๋ฅผ ๊นŠ๊ฒŒ ์ƒ๊ฐํ•˜๋ฉด์„œ ํ’€์–ด๋ด
  ์—ฐํ•„ 5 ํƒ€์™€ ์ง€์šฐ๊ฐœ 45 ๊ฐœ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๊ฒƒ์„ ๋  ์ˆ˜ ์žˆ๋Š” ๋Œ€๋กœ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚จ๊น€์—†์ด ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ฃผ๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ๋ช‡ ๋ช…๊นŒ์ง€ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๊นŒ?
Model:
  ์•„๋ž˜ ๋ฌธ์ œ๋ฅผ ๊นŠ๊ฒŒ ์ƒ๊ฐํ•˜๋ฉด์„œ ํ’€์–ด๋ด…์‹œ๋‹ค:
  ์—ฐํ•„ 5 ํƒ€์™€ ์ง€์šฐ๊ฐœ 45 ๊ฐœ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. ์ด๊ฒƒ์„ ๋  ์ˆ˜ ์žˆ๋Š” ๋Œ€๋กœ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚จ๊น€์—†์ด ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ฃผ๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค. ๋ช‡ ๋ช…๊นŒ์ง€ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๊นŒ?
  ํ’€์ด:
  1. ์—ฐํ•„ 5 ํƒ€๋ฅผ 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ ์„œ ๋ช‡ ๋ช…์—๊ฒŒ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๋จผ์ € ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
  - ๊ฐ ์—ฐํ•„์—๋Š” 12๊ฐœ์˜ ์—ฐํ•„์ด ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ์ด 12 * 5 = 60๊ฐœ์ž…๋‹ˆ๋‹ค.
  - 60๊ฐœ๋ฅผ 1๋ช…๋‹น 1๊ฐœ์”ฉ ๋‚˜๋ˆ„๋ฉด 60๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
  2. ์ง€์šฐ๊ฐœ 45 ๊ฐœ๋ฅผ 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ„์–ด ๋ช‡ ๋ช…์—๊ฒŒ ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
  - 45 ๊ฐœ๋ฅผ 1 ๋ช…๋‹น 1 ๊ฐœ์”ฉ ๋‚˜๋ˆ„๋ฉด 45 ๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
  3. ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ์˜ ๋‘ ๊ฐ€์ง€ ๋ฌผํ’ˆ์„ ํ•จ๊ป˜ ๊ณ ๋ คํ•˜์—ฌ ๊ฐ€์žฅ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์„ ์ฐพ์Šต๋‹ˆ๋‹ค.
  - ์—ฐํ•„๋กœ๋งŒ 60๋ช…, ์ง€์šฐ๊ฐœ๋กœ๋งŒ 45๋ช…์˜ ํ•™์ƒ์—๊ฒŒ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์œผ๋ฏ€๋กœ, ๋‘ ์ข…๋ฅ˜์˜ ๋ฌธ๊ตฌ๋ฅผ ํ•จ๊ป˜ ๊ณ ๋ คํ•  ๋•Œ๋Š” ์ด๋ณด๋‹ค ์ ์€ ์ˆ˜์˜ ํ•™์ƒ์—๊ฒŒ ๋‚˜๋ˆ ์ฃผ์–ด์•ผ ํ•ฉ๋‹ˆ๋‹ค. 
  - ์ด ์ค‘์—์„œ ๊ณตํ†ต์ธ์ˆ˜(common divisor)๋ฅผ ์ฐพ์•„์„œ ์ด๋ฅผ ์ตœ์†Œ ๋‹จ์œ„๋กœ ์„ค์ •ํ•˜๋ฉด ๋ฉ๋‹ˆ๋‹ค.
  - 60๊ณผ 45์˜ ์ตœ๋Œ€๊ณต์•ฝ์ˆ˜(GCD)๋Š” 15์ž…๋‹ˆ๋‹ค.
  4. ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ ๊ฐ๊ฐ์„ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๋ช‡ ๊ฐœ์”ฉ ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ๋Š”์ง€ ๊ตฌํ•ฉ๋‹ˆ๋‹ค.
  - ์—ฐํ•„์€ 60 / 15 = 4๊ฐœ์”ฉ, ์ด 4 * 12 = 48๊ฐœ์˜ ์—ฐํ•„์ด ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
  - ์ง€์šฐ๊ฐœ๋Š” 45 / 15 = 3๊ฐœ์”ฉ, ์ด 3 * 1 = 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
  5. ์ตœ์ข…์ ์œผ๋กœ, ๊ฐ€์žฅ ๋งŽ์€ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์€ ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ๋ฅผ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๊ฐ ํ•™์ƒ์—๊ฒŒ 4๊ฐœ์˜ ์—ฐํ•„๊ณผ 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๋ฅผ ์ œ๊ณตํ•˜๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
  - ์ด ๊ฒฝ์šฐ ์ด 48 + 3 = 51๊ฐœ์˜ ๋ฌผํ’ˆ์„ ์‚ฌ์šฉํ•˜์—ฌ 15๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
    ๊ฒฐ๋ก : ์—ฐํ•„๊ณผ ์ง€์šฐ๊ฐœ ๊ฐ๊ฐ์„ GCD(15)๋กœ ๋‚˜๋ˆ„์–ด ๊ฐ ํ•™์ƒ์—๊ฒŒ 4๊ฐœ์˜ ์—ฐํ•„๊ณผ 3๊ฐœ์˜ ์ง€์šฐ๊ฐœ๋ฅผ ์ œ๊ณตํ•˜๋Š” ๋ฐฉ๋ฒ•์œผ๋กœ ์ตœ๋Œ€ 15๋ช…์˜ ํ•™์ƒ๋“ค์—๊ฒŒ ๋˜‘๊ฐ™์ด ๋‚˜๋ˆ„์–ด ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
Writting[CLICK TO EXPAND]
User:
  ์•„๋ž˜ ๋ฌธ์žฅ์„ ๋ณด๊ณ  ๋ฌธ๋ฒ•์ ์œผ๋กœ ํ‹€๋ฆฐ๋ถ€๋ถ„์„ ์ง€์ ํ•ด์ค˜
  ๊ทธ๋Š” ์„œ์Šด์น˜ ์•Š๊ณ  ๋น„ํ‰ํ•œ๋‹ค.
Model:
  ์„œ์Šด์น˜"๋ผ๋Š” ๋‹จ์–ด๋Š” "์„œ์Šด"์ด๋ผ๋Š” ๋™์‚ฌ์™€ "์น˜"๋ผ๋Š” ์ ‘๋ฏธ์‚ฌ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๋งŒ๋“  ๋‹จ์–ด์ž…๋‹ˆ๋‹ค. ์ด ๋‹จ์–ด๋Š” "์„œ์Šด"์˜ ์˜๋ฏธ๋ฅผ ๋ฐ˜๋ณต์ ์œผ๋กœ ํ‘œํ˜„ํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋˜๋Š” ์กฐ๋™์‚ฌ์  ์šฉ๋ฒ•์œผ๋กœ, "์„œ์Šด"์ด๋ž€ ๋™์‚ฌ์˜ ๋ฐ˜๋ณต์ ์ธ ํ–‰๋™์„ ๊ฐ•์กฐํ•ฉ๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ๋ฌธ์žฅ์—์„œ "์„œ์Šด์น˜"๋ผ๋Š” ๋‹จ์–ด๋Š” ์ค‘๋ณต์ ์œผ๋กœ ์‚ฌ์šฉ๋˜์–ด ๋ฌธ๋ฒ•์ ์œผ๋กœ ํ‹€๋ฆฐ ๋ถ€๋ถ„์ž…๋‹ˆ๋‹ค.

  ์ •๋‹ต์€ ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค:
  ๊ทธ๋Š” ์„œ์Šด์—†์ด ๋น„ํ‰ํ•œ๋‹ค.
User:
  ์œค๋™์ฃผ ์‹œ์ธ์˜ "๋ณ„ ํ—ค๋Š” ๋ฐค"์„ ๋ณด๊ณ  ๋‹น์‹œ ์‹œ๋Œ€์ƒ์„ ๊ณ ๋ คํ•ด์„œ ํ•ด์„ํ•ด๋ด. ๊ทธ๋ฆฌ๊ณ  ์ด๋ฅผ ์ž‘๊ฐ€์˜ ๋…๋ฐฑํ˜•์‹์œผ๋กœ ๋‹ค์‹œ ์ž‘์„ฑํ•ด๋ด.
Model:
  ์œค๋™์ฃผ๋Š” 1941๋…„ ์ผ๋ณธ ์ œ๊ตญ์ฃผ์˜ ์น˜ํ•˜์—์„œ ์ด ์ž‘ํ’ˆ์„ ์“ฐ๋ฉด์„œ, ๊ฐ•์••์ ์ธ ์ƒํ™ฉ ์†์—์„œ๋„ ์ž์‹ ์˜ ์ •์ฒด์„ฑ๊ณผ ๋ฌธํ™”์— ๋Œ€ํ•œ ์• ์ฐฉ์„ ํ‘œํ˜„ํ•˜๊ณ ์ž ํ–ˆ์Šต๋‹ˆ๋‹ค. ๊ทธ๋Š” ํ•˜๋Š˜์— ๊ฐ€๋“ ์ฐฌ ๋ณ„๋“ค์„ ๋ณด๋ฉฐ ๊ทธ ์†์— ํ•˜๋‚˜ ๋‘˜ ์ƒˆ๊ฒจ์ง€๋Š” ๋ณ„๋“ค์ด ์žˆ๋‹ค๊ณ  ํ‘œํ˜„ํ–ˆ์Šต๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ๋ณ„๋“ค์€ ๊ฐ๊ฐ ์ถ”์–ต, ์‚ฌ๋ž‘, ์“ธ์“ธํ•จ, ๋™๊ฒฝ, ์‹œ ๋“ฑ ๋‹ค์–‘ํ•œ ๊ฐ์ •์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
  ์œค๋™์ฃผ๋Š” ์ด ๋ณ„๋“ค ์ค‘ ํ•˜๋‚˜์— ์–ด๋จธ๋‹ˆ๋ฅผ ๋ถ€๋ฅด๋ฉฐ ๋ฉ€๋ฆฌ ๋–จ์–ด์ ธ ์žˆ๋Š” ๊ฒƒ์„ ๊ทธ๋ฆฌ์›Œํ•˜๋ฉฐ, ์ž์‹ ์˜ ์ด๋ฆ„์ž๋ฅผ ์–ธ๋• ์œ„์— ์“ฐ๊ณ  ํ™์œผ๋กœ ๋ฎ์–ด ๋ฒ„๋ฆฐ๋‹ค๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ํ–‰๋™์€ ์ž์‹ ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ , ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ์œผ๋กœ ๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
  ์œค๋™์ฃผ๋Š” ๋˜ํ•œ ์ž์‹ ์ด ์ฃฝ๊ณ  ๋‚˜๋ฉด ๋ฌด๋ค ์œ„์— ํŒŒ๋ž€ ์ž”๋””๊ฐ€ ํ”ผ์–ด๋‚˜๋“ฏ์ด ์ž์‹ ์˜ ์ด๋ฆ„์ž ๋ฌปํžŒ ์–ธ๋• ์œ„์—๋„ ํ’€์ด ๋ฌด์„ฑํ•  ๊ฒƒ์ด๋ผ๊ณ  ๋งํ•ฉ๋‹ˆ๋‹ค. ์ด๋Š” ๋‹น์‹œ์˜ ์‚ฌํšŒ์ƒ๊ณผ ์ž‘๊ฐ€์˜ ๋‚ด๋ฉด์„ ๋ฐ˜์˜ํ•˜๊ณ  ์žˆ์œผ๋ฉฐ, ํ•œ๊ตญ์ธ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ  ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ, ๊ทธ๋ฆฌ๊ณ  ์ฃฝ์Œ ์ดํ›„์— ์ž์‹ ์˜ ์กด์žฌ๋ฅผ ๋‚จ๊ฒจ๋‘๊ณ  ์‹ถ๋‹ค๋Š” ๋ฐ”๋žŒ์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
  ์ด ์‹œ๋ฅผ ์ž‘๊ฐ€์˜ ๋…๋ฐฑํ˜•์‹์œผ๋กœ ๋‹ค์‹œ ์ž‘์„ฑํ•˜๋ฉด ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค:
  "์ €๋Š” ์ด ๋ณ„๋“ค์ด ๋„ˆ๋ฌด๋‚˜ ๋งŽ์€ ๊ฒƒ ๊ฐ™์•„์š”. ํ•˜๋‚˜ ๋‘˜ ์ƒˆ๊ฒจ์ง€๋Š” ๋ณ„๋“ค ์ค‘์—๋Š” ์ถ”์–ต๋„ ์žˆ๊ณ , ์‚ฌ๋ž‘๋„ ์žˆ๊ณ , ์“ธ์“ธํ•จ๊ณผ ๋™๊ฒฝ๋„ ์žˆ์–ด์š”. ๊ทธ๋ฆฌ๊ณ  ์–ด๋จธ๋‹ˆ, ๋‹น์‹ ์€ ๋ฉ€๋ฆฌ ๋ถ๊ฐ„๋„์— ๊ณ„์‹  ๊ฑด๊ฐ€์š”? ์ €๋Š” ๋‹น์‹ ์„ ๋ถ€๋ฅด๊ณ  ์‹ถ์–ด์š”.
  ์ €์˜ ์ด๋ฆ„์ž๋Š” ์–ธ๋• ์œ„์— ์“ฐ๊ณ  ํ™์œผ๋กœ ๋ฎ์–ด ๋ฒ„๋ ธ์–ด์š”. ๋”ด์€ ๋ฐค์„ ์ƒˆ์›Œ ์šฐ๋Š” ๋ฒŒ๋ ˆ์ฒ˜๋Ÿผ ๋ถ€๋„๋Ÿฌ์šด ์ด๋ฆ„์„ ์Šฌํผํ•˜๋Š” ์ด์œ ๊ฐ€ ์žˆ์–ด์š”. ํ•˜์ง€๋งŒ ๊ฒจ์šธ์ด ์ง€๋‚˜๊ณ  ๋‚˜์˜ ๋ณ„์—๋„ ๋ด„์ด ์˜ค๋ฉด, ๋ฌด๋ค ์œ„์— ํŒŒ๋ž€ ์ž”๋””๊ฐ€ ํ”ผ์–ด๋‚˜๋“ฏ์ด ์ €์˜ ์ด๋ฆ„์ž ๋ฌปํžŒ ์–ธ๋• ์œ„์—์„œ๋„ ํ’€์ด ๋ฌด์„ฑํ•  ๊ฑฐ์˜ˆ์š”.
  ์ €๋Š” ์ด ๋ณ„๋“ค์„ ๋ณด๊ณ , ์ž์‹ ์˜ ์ •์ฒด์„ฑ์„ ํ™•์ธํ•˜๊ณ  ์‹ถ์–ด์š”. ์žƒ์–ด๋ฒ„๋ฆฐ ๊ฒƒ์„ ๋˜์ฐพ์œผ๋ ค๋Š” ๋…ธ๋ ฅ์„ ํ•˜๊ณ  ์‹ถ์–ด์š”. ์ฃฝ์Œ ์ดํ›„์—๋„ ์ž์‹ ์˜ ์กด์žฌ๋ฅผ ๋‚จ๊ฒจ๋‘๊ณ  ์‹ถ์–ด์š”."
Logical Reasoning[CLICK TO EXPAND]
User:
  ์„ธ์ข…๋Œ€์™•์˜ ๋งฅ๋ถํ”„๋กœ ๋˜์ง ์‚ฌ๊ฑด์— ๋Œ€ํ•ด ์„ค๋ช…ํ•ด์ค˜
Model:
  ์„ธ์ข…๋Œ€์™•์ด ๋งฅ๋ถํ”„๋กœ๋ฅผ ๋˜์ง„ ์‚ฌ๊ฑด์€ ์‚ฌ์‹ค๋ฌด๊ทผํ•œ ์ด์•ผ๊ธฐ์ž…๋‹ˆ๋‹ค. ์„ธ์ข…๋Œ€์™•์€ ์กฐ์„  ์ œ4๋Œ€ ๊ตญ์™•์œผ๋กœ 1418๋…„๋ถ€ํ„ฐ 1450๋…„๊นŒ์ง€ ์žฌ์œ„ํ–ˆ์Šต๋‹ˆ๋‹ค. ๊ทธ๋Š” ๊ณผํ•™, ๋ฌธํ•™, ์˜ˆ์ˆ  ๋“ฑ ๋‹ค์–‘ํ•œ ๋ถ„์•ผ์— ๊ด€์‹ฌ์„ ๊ฐ–๊ณ  ์—ฐ๊ตฌํ•˜์˜€์œผ๋ฉฐ, ํŠนํžˆ ํ•œ๊ธ€ ์ฐฝ์ œ์™€ ์ฒœ๋ฌธํ•™์— ํฐ ๊ณตํ—Œ์„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
  ํ•œํŽธ ๋งฅ๋ถํ”„๋กœ๋Š” ์• ํ”Œ์ด ์ƒ์‚ฐํ•˜๋Š” ๋…ธํŠธ๋ถ ์ปดํ“จํ„ฐ๋กœ, ์„ธ์ข…๋Œ€์™• ์‹œ๋Œ€์˜ ๊ธฐ์ˆ ๋กœ๋Š” ์กด์žฌํ•  ์ˆ˜ ์—†๋Š” ์ œํ’ˆ์ž…๋‹ˆ๋‹ค. ๋”ฐ๋ผ์„œ ์„ธ์ข…๋Œ€์™•์ด ๋งฅ๋ถํ”„๋กœ๋ฅผ ๋˜์ง„ ์‚ฌ๊ฑด์€ ์‚ฌ์‹ค๊ณผ ๋งž์ง€ ์•Š๋Š” ์ด์•ผ๊ธฐ๊ฐ€ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
Coding [CLICK TO EXPAND]
User:
  PyTorch๋ฅผ ์‚ฌ์šฉํ•ด์„œ ๊ฐ„๋‹จํ•œ CNN์„ ๊ตฌํ˜„ํ•ด๋ด.
Model:
  ๋„ค, ๋ฌผ๋ก ์ด์—์š”! PyTorch๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ๊ฐ„๋‹จํ•œ CNN์„ ๊ตฌํ˜„ํ•˜๋Š” ์˜ˆ์ œ ์ฝ”๋“œ๋ฅผ ๋ณด์—ฌ๋“œ๋ฆด๊ฒŒ์š”.
  ์šฐ์„ , ํ•„์š”ํ•œ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋ฅผ ๊ฐ€์ ธ์™€์•ผ ํ•ด์š”. PyTorch์˜ `torch`์™€ `nn` ๋ชจ๋“ˆ์ด ํ•„์š”ํ•ด์š”. 
```python
import torch\nimport torch.nn as nn
```
๊ทธ ๋‹ค์Œ, ๊ฐ„๋‹จํ•œ CNN ๋ชจ๋ธ์„ ์ •์˜ํ•  ๊ฑฐ์˜ˆ์š”. ์ด ๊ฒฝ์šฐ์—๋Š” 2๊ฐœ์˜ ์ปจ๋ณผ๋ฃจ์…˜ ๋ ˆ์ด์–ด์™€ 3๊ฐœ์˜ ํ’€๋ง ๋ ˆ์ด์–ด๋กœ ๊ตฌ์„ฑ๋œ ๋ชจ๋ธ์ด์—์š”.
  ```python
class SimpleCNN(nn.Module):
def __init__(self):
  super(SimpleCNN, self).__init__()
  self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
  self.pool = nn.MaxPool2d(2, 2)
  self.conv2 = nn.Conv2d(10, 20, kernel_size=5)

def forward(self, x):
  x = self.pool(torch.relu(self.conv1(x)))
  x = self.pool(torch.relu(self.conv2(x)))
  return x
```
์ด์ œ ๋ชจ๋ธ์„ ์ดˆ๊ธฐํ™”ํ•˜๊ณ , ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ์ค€๋น„ํ•ด์•ผ ํ•ด์š”. ์—ฌ๊ธฐ์„œ๋Š” ์ž„์˜์˜ 28x28 ํฌ๊ธฐ์˜ ์ด๋ฏธ์ง€ ๋ฐ์ดํ„ฐ๋ฅผ ์ƒ์„ฑํ–ˆ์–ด์š”.
```python
model = SimpleCNN()
input_data = torch.randn(1, 1, 28, 28)
```
๋งˆ์ง€๋ง‰์œผ๋กœ, ๋ชจ๋ธ์— ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ๋„ฃ์–ด ์ถœ๋ ฅ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์–ด์š”.
```python
output = model(input_data)
print(output.shape)
```
์ด๋ ‡๊ฒŒ ํ•˜๋ฉด ๊ฐ„๋‹จํ•œ CNN ๋ชจ๋ธ์„ PyTorch๋ฅผ ์‚ฌ์šฉํ•ด ๊ตฌํ˜„ํ•˜๊ณ , ์ž…๋ ฅ ๋ฐ์ดํ„ฐ๋ฅผ ํ†ตํ•ด ์ถœ๋ ฅ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ์–ด์š”. ๋ฌผ๋ก  ์‹ค์ œ๋กœ๋Š” ๋” ๋งŽ์€ ๋ ˆ์ด์–ด๋‚˜ ํŒŒ๋ผ๋ฏธํ„ฐ ํŠœ๋‹ ๋“ฑ์ด ํ•„์š”ํ•˜์ง€๋งŒ, ์ด ์ฝ”๋“œ๋Š” ๊ธฐ๋ณธ์ ์ธ CNN ๊ตฌ์กฐ๋ฅผ ๋ณด์—ฌ์ฃผ๋Š” ์˜ˆ์ œ์ผ ๋ฟ์ด์—์š”. ๋” ๊ถ๊ธˆํ•œ ์ ์ด ์žˆ์œผ๋ฉด ์–ธ์ œ๋“ ์ง€ ๋ฌผ์–ด๋ด ์ฃผ์„ธ์š”!
You can find more examples at [our project page](https://yonsei-mir.github.io/AkaLLaMA-page) ## Special Thanks - Data Center of the Department of Artificial Intelligence and Jeong Mee Koh at Yonsei University for the computation resources ## Comments - Title image generated by DALLยทE 3