komt-llama-2-7b-lora

This model fine-tuned the aaa model using PEFT-LoRA.

The "komt-llama-2-7b" model was developed using a multi-task instruction technique aimed at enhancing Korean language performance. For more details, please refer to the GitHub Repository. Please refer below for more detailed information.

For more detailed information, please refer to the https://huggingface.co/davidkim205/komt-Llama-2-7b-chat-hf.

Model Details

• Model Developers : davidkim(changyeon kim)
• Repository : https://github.com/davidkim205/komt
• Lora target modules : q_proj, o_proj, v_proj, gate_proj, down_proj, k_proj, up_proj
• Model Size : 80MB
• Model Architecture : komt-llama-2-7b is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning by multi-task instruction

Dataset

korean multi-task instruction dataset

Prompt Template

### instruction: {prompt}

### Response: 

Examples:

### instruction: 자동차 종합(정기)검사 의무기간은 얼마인가요?

### Response:

response:

### instruction: 자동차 종합(정기)검사 의무기간은 얼마인가요?

### Response: 자동차 종합(정기)검사 의무기간은 2년입니다. 이 기간 동안 검사를 받지 않으면 과태료가 부과됩니다. 자동차 종합(정기)검사 의무기간은 2013년 12월 31일부터 시행되었습니다

Usage

After downloading from GitHub, please install as follows:

git clone https://github.com/davidkim205/komt
cd komt
pip install -r lora/requirements_lora.txt

• Requirements Python >=3.8. Linux distribution (Ubuntu, MacOS, etc.) + CUDA > 10.0. Refer https://github.com/TimDettmers/bitsandbytes#tldr

import torch

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from transformers import StoppingCriteria, StoppingCriteriaList
from transformers import TextStreamer, GenerationConfig
from peft import PeftModel, PeftConfig

class LocalStoppingCriteria(StoppingCriteria):

    def __init__(self, tokenizer, stop_words = []):
        super().__init__()

        stops = [tokenizer(stop_word, return_tensors='pt', add_special_tokens = False)['input_ids'].squeeze() for stop_word in stop_words]
        print('stop_words', stop_words)
        print('stop_words_ids', stops)
        self.stop_words = stop_words
        self.stops = [stop.cuda() for stop in stops]
        self.tokenizer = tokenizer
    def _compare_token(self, input_ids):
        for stop in self.stops:
            if len(stop.size()) != 1:
                continue
            stop_len = len(stop)
            if torch.all((stop == input_ids[0][-stop_len:])).item():
                return True

        return False
    def _compare_decode(self, input_ids):
        input_str = self.tokenizer.decode(input_ids[0])
        for stop_word in self.stop_words:
            if input_str.endswith(stop_word):
                return True
        return False

    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor):
        input_str = self.tokenizer.decode(input_ids[0])
        for stop_word in self.stop_words:
            if input_str.endswith(stop_word):
                return True
        return False

#
# config
peft_model_name = 'davidkim205/komt-Llama-2-7b-chat-hf-lora'
model_name = 'davidkim205/komt-Llama-2-7b-chat-hf'
instruction_prefix = "### instruction: "
input_prefix = "### input: "
answer_prefix = "### Response: "
endoftext = "<|end|>"
stop_words = [endoftext, '<s>', '###']
generation_config = GenerationConfig(
    temperature=0.9,
    top_p=0.7,
    top_k=100,
    max_new_tokens=2048,
    early_stopping=True,
    do_sample=True,
)
#
# create model
config = PeftConfig.from_pretrained(peft_model_name)
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)
model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=bnb_config,
                                             device_map="auto")
model = PeftModel.from_pretrained(model, peft_model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
stopping_criteria = StoppingCriteriaList([LocalStoppingCriteria(tokenizer=tokenizer, stop_words=stop_words)])
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
model.eval()

#
# generate
prompt = f"### instruction: 자동차 종합(정기)검사 의무기간은 얼마인가요?.\n\n### Response:"
gened = model.generate(
    **tokenizer(
        prompt,
        return_tensors='pt',
        return_token_type_ids=False
    ).to('cuda'),
    generation_config=generation_config,
    eos_token_id=model.config.eos_token_id,
    stopping_criteria=stopping_criteria,
    streamer=streamer
)
output_text = tokenizer.decode(gened[0], skip_special_tokens=True)

print('--------------------')
print(output_text)

response:

nlp는 자연어 처리의 약자로, 자연어를 사용하여 인간과 컴퓨터 간의 상호 작용을 다루는 분야입니다. 컴퓨터와 인간이 서로 상호 작용하는 데 사용되는 언어와 기술을 포함하며, 컴퓨터는 인간의 언어를 처리하고 분석하여 인간의 작업을 돕거나 작업을 자동화하는 데 사용됩니다. 따라서 컴퓨터가 컴퓨터에서 작업하는 데 사용되는 컴퓨터 프로그램이나 프로그램과 비슷하게 인간도 자신의 작업에 사용되는 컴퓨터 프로그램과 비슷한 방식으로 작업할 수 있습니다.

Hardware and Software

• nvidia driver : 535.54.03
• CUDA Version: 12.2

Framework versions

• PEFT 0.4.0

Training

Refer github

Model Benchmark

• Used EleutherAI's lm-evaluation-harness https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot

Korean Semantic Textual Similarity

Example Output

Please refer to the GitHub link below for performance results of each model. https://github.com/davidkim205/komt/tree/main/eval_results

Original model card: Meta's Llama 2 13B-chat

Meta developed and 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.

Llama 2 family of models. Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. The 70B version uses 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/

Research Paper More information can be found in the paper "Llama-2: Open Foundation and Fine-tuned Chat Models", available at https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/.

Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README.

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.

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.

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.

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.

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).

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/