README.md

- Original model is [yanolja/EEVE-Korean-Instruct-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0)
- quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp)


### Usage
requirements
```
# GPU model
CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir --verbose

# CPU
CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir --verbose

pip install huggingface_hub
```

```
from huggingface_hub import hf_hub_download
from llama_cpp import Llama

import time
from pprint import pprint


# download model
model_name_or_path = "heegyu/EEVE-Korean-Instruct-10.8B-v1.0-GGUF" # repo id
# 4bit
model_basename = "ggml-model-Q4_K_M.gguf" # file name

model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
print(model_path)


# CPU
# lcpp_llm = Llama(
#     model_path=model_path,
#     n_threads=2,
#     )

# GPU에서 사용하려면 아래 코드로 실행
lcpp_llm = Llama(
    model_path=model_path,
    n_threads=2, # CPU cores
    n_batch=512, # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
    n_gpu_layers=43, # Change this value based on your model and your GPU VRAM pool.
    n_ctx=4096, # Context window
)


prompt_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\nHuman: {prompt}\nAssistant:\n"
text = '한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.\n\n(A) 경성\n(B) 부산\n(C) 평양\n(D) 서울\n(E) 전주'

prompt = prompt_template.format(prompt=text)

start = time.time()
response = lcpp_llm(
    prompt=prompt,
    max_tokens=256,
    temperature=0.5,
    top_p=0.95,
    top_k=50,
    stop = ['</s>'], # Dynamic stopping when such token is detected.
    echo=True # return the prompt
)
pprint(response)
print(time.time() - start)
```

실행결과 (Colab T4 GPU)
```
llama_print_timings:        load time =     942.53 ms
llama_print_timings:      sample time =      27.60 ms /    37 runs   (    0.75 ms per token,  1340.43 tokens per second)
llama_print_timings: prompt eval time =     942.29 ms /    83 tokens (   11.35 ms per token,    88.08 tokens per second)
llama_print_timings:        eval time =    4530.31 ms /    36 runs   (  125.84 ms per token,     7.95 tokens per second)
llama_print_timings:       total time =    5648.42 ms /   119 tokens
{'choices': [{'finish_reason': 'stop',
              'index': 0,
              'logprobs': None,
              'text': 'A chat between a curious user and an artificial '
                      'intelligence assistant. The assistant gives helpful, '
                      "detailed, and polite answers to the user's questions.\n"
                      'Human: 한국의 수도는 어디인가요? 아래 선택지 중 골라주세요.\n'
                      '\n'
                      '(A) 경성\n'
                      '(B) 부산\n'
                      '(C) 평양\n'
                      '(D) 서울\n'
                      '(E) 전주\n'
                      'Assistant:\n'
                      '한국은 동아시아에 위치한 국가로 공식적으로 대한민국이라고 불립니다. 서울은 대한민국의 수도입니다. '
                      '따라서 정답은 (D) 서울입니다.'}],
 'created': 1710404368,
 'id': 'cmpl-af889267-f64e-4516-b0a3-5c8b918d0e36',
 'model': '/root/.cache/huggingface/hub/models--heegyu--EEVE-Korean-Instruct-10.8B-v1.0-GGUF/snapshots/ff014aa6d73ffa8a2857085261cb7a4e6c630bfe/ggml-model-Q4_K_M.gguf',
 'object': 'text_completion',
 'usage': {'completion_tokens': 36, 'prompt_tokens': 83, 'total_tokens': 119}}
5.662428140640259
```