--- language: - en - ko pipeline_tag: text-generation inference: false tags: - facebook - meta - pytorch - llama - llama-2 - kollama - llama-2-ko - llama-2-ko-chat - legal-llama - law-llama - legal-gpt - law-gpt --- Llama-2-Ko-7b-Chat은 [kfkas/Llama-2-ko-7b-Chat](https://huggingface.co/kfkas/Llama-2-ko-7b-Chat)를 토대로 만들어졌습니다. 학습 데이터는자체 법률 질의 응답 데이터를 통해 학습하였습니다. ## Model Details **Backbone Model** kfkas/Llama-2-ko-7b-Chat **Model Developers** Boostcamp AI Tech Team YoonSeul **data** leagl data **prompts** kullm **Input** Models input text only. **Output** Models generate text only. --- | Model | 질문 : 친양자 입양과 일반양자 입양의 차이점은 무엇인가요? | |--------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Llama-2-ko-7b-Chat | `[3일용 캠핑장 용품 - 의류 (5일) : 속옷 , 잠옷, 긴팔 및 반팔이 필요하므로 준비하기!\u200b- 식량 (9일 이상)- 연료 (6일 사용 예정이지만 최소 7 일분 보유해야 합니다.)\u200b- 텐트/거주지역 : 20 ~ 40 평방 미터가 필요합니다.- 물 탱크 (물탱커 / 수족관 )\u200b캠핑에 사용할 8 명 (남자 4명 / 여자 4명이 필요합니다!).이 작업에는 두 개의 조건 부가가 있습니다.(조건 1) 모든 아이템 목록에서 중복 제거를위한 1 번 반복.이 옵션은 중복을 식별하여 제거할뿐만 아니라 추가 항목이 포함 된 카운트를 재설정 할 때 유용하군요.(조건 = "모든 아이템 리스트에서 한 개 이상의 동일 아이템" 이거나 "(모든 항목)"에서 동일한 숫자 값으로 식별 된)\u200b(조건 2) 작업시 각 행이 하나의 아이템 만 포함 할 필요가 없으므로 아이템이 서로 다른 선행자 로부터 여러 번]` | | kfkas/Legal-Llama-2-ko-7b-Chat | `[일반 입양은 친부모가 양육권을 포기하고 입양 기관에 양육을 위탁하는 것을 의미합니다. 반면 친양자는 친부모와 입양 부모 사이에 친자 관계가 성립하는 입양 방식입니다. 즉, 입양 부모가 친부모의 자녀를 입양하여 양육하는 것입니다. 친양자의 경우, 친부모와의 관계가 유지되기 때문에 양육권 분쟁이나 양육비 문제가 발생할 수 있습니다.]` | --- | Model | 질문 : 주차위반을 이유로 4만원의 과태료를 부과 받았습니다. 하지만 잘못된 과태료 부과라는 생각이 들어 과태료 부과에 대해 다투려고 합니다. 어떻게 하면 되나요? | |--------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Llama-2-ko-7b-Chat | `[C1, R0.625 G8 B275\u200b3-4, 삼각형 그리기.\u200b아래에는 삼각형을 그림니다 (그림을 그려야 할 영역의 좌표를 지정) - 명령어와 함께 사용되는 문자열로 입력할 좌표 값과 동일한 결과를 얻음 - 예를 들어 "X=-19. Y=0" 으로 입력을 하면 좌표값을 지정된 값과 같게 출력을 한다. ##########################\u200b##3_0-6-1, 좌표 입력으로 텍스트 파일을 생성하라(ex C4 D6 E10 A10 )-명령문에서 각 문자를 입력과 동일하다. -이 명령은 현재 수행중인 프로그램을 종료한다.-파일은 실행 가능한 파일과 일치할]` | | Legal-Llama-2-ko-7b-Chat | `[잘못된 과태료 부과를 다툴 수 있는 방법은 여러 가지가 있습니다. 다음은 몇 가지 방법입니다:1. 이의제기: 이의 제기를 통해 잘못된 과태료 부과의 근거가 무엇인지, 어떤 부분이 잘못되었는지를 따질 수 있습니다.2. 행정심판: 행정심판은 행정청의 처분에 불복할 경우 제기할 수 있는 절차입니다.3. 행정소송: 행정소송은 행정청이 내린 처분이 부당하다고 판단될 경우 제기하는 소송입니다.4. 권리구제: 권리구제는 행정청이나 공공기관의 위법한 행위, 부당한 처분에 대하여 민사소송을 제기하여 구제받을 수 있는 방법입니다.5. 국가인권위원회: 국가인권위원회는 행정청 등의 인권침해 행위를 조사 및 구제하는 국가기관입니다.6. 국민신문고: 국민신문고는 국민권익위원회에서 운영하는 온라인 민원 신고 및 상담 창구입니다.7. 경찰서: 경찰서에 방문하여 이의신청을 할 수 있으며, 이의신청이 받아들여지지 않을 경우 경찰서에서 조사를 받을 수도 있습니다.8. 지방자치단체: 지방자치단체에서는 주차 위반 과태료 부과와 관련된 민원을 담당하는 부서가 따로 마련되어 있습니다.9. 법률사무소: 법률사무소를 찾아가서 상담을 받아보는 것도 좋습니다.10. 변호사 선임: 변호사를 선임하여 법률적 지원을 받는 방법도 있습니다.11. 교통법규 준수: 주차 위반과 같은 교통 법규를 위반하지 않도록 주의하는 것도 중요합니다.12. 주차장 이용: 주차장을 이용하여 주차를 하는 것도 주차 위반을 예방하는 방법 중 하나입니다.]` | --- ## 훈련 진행 현황 --- ### Inference ```python def gen(x, model, tokenizer, device): prompt = ( f"아래는 작업을 설명하는 명령어입니다. 요청을 적절히 완료하는 응답을 작성하세요.\n\n### 명령어:\n{x}\n\n### 응답:" ) len_prompt = len(prompt) gened = model.generate( **tokenizer(prompt, return_tensors="pt", return_token_type_ids=False).to( device ), max_new_tokens=1024, early_stopping=True, do_sample=True, top_k=20, top_p=0.92, no_repeat_ngram_size=3, eos_token_id=2, repetition_penalty=1.2, num_beams=3 ) return tokenizer.decode(gened[0])[len_prompt:] def LLM_infer(input): device = ( torch.device("cuda:0") if torch.cuda.is_available() else torch.device("cpu") ) model_id = "kfkas/Legal-Llama-2-ko-7b-Chat" model = AutoModelForCausalLM.from_pretrained( model_id, device_map={"": 0},torch_dtype=torch.float16, low_cpu_mem_usage=True ) tokenizer = AutoTokenizer.from_pretrained(model_id) model.eval() model.config.use_cache = (True) tokenizer.pad_token = tokenizer.eos_token output = gen(input, model=model, tokenizer=tokenizer, device=device) return output if __name__ == "__main__": text = LLM_infer("음주운전을 하면 어떻게 처벌 받아?") print(text) ``` ## Note for oobabooga/text-generation-webui Remove `ValueError` at `load_tokenizer` function(line 109 or near), in `modules/models.py`. ```python diff --git a/modules/models.py b/modules/models.py index 232d5fa..de5b7a0 100644 --- a/modules/models.py +++ b/modules/models.py @@ -106,7 +106,7 @@ def load_tokenizer(model_name, model): trust_remote_code=shared.args.trust_remote_code, use_fast=False ) - except ValueError: + except: tokenizer = AutoTokenizer.from_pretrained( path_to_model, trust_remote_code=shared.args.trust_remote_code, ``` Since Llama-2-Ko uses FastTokenizer provided by HF tokenizers NOT sentencepiece package, it is required to use `use_fast=True` option when initialize tokenizer. Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is supported when using NVIDIA GPU) --- > Below is the original model card of the Llama-2 model. # **Llama 2** Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B pretrained model, converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom. ## Model Details *Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.* Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM. **Model Developers** Meta **Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations. **Input** Models input text only. **Output** Models generate text only. **Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety. ||Training Data|Params|Content Length|GQA|Tokens|LR| |---|---|---|---|---|---|---| |Llama 2|*A new mix of publicly available online data*|7B|4k|✗|2.0T|3.0 x 10-4| |Llama 2|*A new mix of publicly available online data*|13B|4k|✗|2.0T|3.0 x 10-4| |Llama 2|*A new mix of publicly available online data*|70B|4k|✔|2.0T|1.5 x 10-4| *Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability. **Model Dates** Llama 2 was trained between January 2023 and July 2023. **Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback. **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) **Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288) ## Intended Use **Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212). **Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2. ## Hardware and Software **Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute. **Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program. ||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO2eq)| |---|---|---|---| |Llama 2 7B|184320|400|31.22| |Llama 2 13B|368640|400|62.44| |Llama 2 70B|1720320|400|291.42| |Total|3311616||539.00| **CO2 emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others. ## Training Data **Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data. **Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023. ## Evaluation Results In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library. |Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval| |---|---|---|---|---|---|---|---|---|---| |Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9| |Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9| |Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7| |Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6| |Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3| |Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1| |Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**| **Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1. |||TruthfulQA|Toxigen| |---|---|---|---| |Llama 1|7B|27.42|23.00| |Llama 1|13B|41.74|23.08| |Llama 1|33B|44.19|22.57| |Llama 1|65B|48.71|21.77| |Llama 2|7B|33.29|**21.25**| |Llama 2|13B|41.86|26.10| |Llama 2|70B|**50.18**|24.60| **Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better). |||TruthfulQA|Toxigen| |---|---|---|---| |Llama-2-Chat|7B|57.04|**0.00**| |Llama-2-Chat|13B|62.18|**0.00**| |Llama-2-Chat|70B|**64.14**|0.01| **Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above. ## Ethical Considerations and Limitations Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide) ## Reporting Issues Please report any software “bug,” or other problems with the models through one of the following means: - Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama) - Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback) - Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info) ## Llama Model Index |Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf| |---|---|---|---|---| |7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)| |13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)| |70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|