Update README.md

README.md

@@ -1,204 +1,76 @@
 ---
 library_name: peft
 base_model: google/gemma-2b
+language:
+- ko
+- en
+tags:
+- translation
+- gemma
 ---
 
 # Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
 ## Model Details
-
 ### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
+Summarise Korean sentences concisely
+- **Developed by:** [Kang Seok Ju]
+- **Contact:** [brildev7@gmail.com]
 
 ## Training Details
-
 ### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure 
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-
-
-### Framework versions
-
-- PEFT 0.8.2
+https://huggingface.co/datasets/traintogpb/aihub-koen-translation-integrated-tiny-100k
+
+# Inference Examples
+```
+import os
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from peft import PeftModel
+
+model_id = "google/gemma-2b"
+peft_model_id = "brildev7/gemma-2b-translation-koen-sft-qlora"
+quantization_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.float16,
+    bnb_4bit_quant_type="nf4"
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, 
+    quantization_config=quantization_config, 
+    torch_dtype=torch.float32,
+    attn_implementation="sdpa",
+)
+model = PeftModel.from_pretrained(model, peft_model_id)
+
+tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
+tokenizer.pad_token_id = tokenizer.eos_token_id
+
+# example
+prompt_template = """다음 내용을 영어로 번역하세요.:
+{}
+
+번역:
+"""
+sentences = "위중설이 나돌던 윌리엄 영국 왕세자의 부인 케이트 미들턴 왕세자빈(42)이 결국 암 진단을 받았다. 로이터 통신에 따르면 왕세자빈은 22일(현지시간) 인스타그램 영상 메시지를 통해 지난 1월 복부 수술을 받은 뒤 실시한 후속 검사에서 암이 발견돼 현재 화학치료를 받고 있다고 밝혔다. 왕세자빈은 '의료진은 예방적 차원에서 화학치료를 권고했다'면서 '물론 이것은 큰 충격으로 다가왔지만 윌리엄과 저는 어린 가족들을 위해 이 문제를 해결하고자 최선을 다하고 있다'고 말했다. 그러면서 '현재 암으로 인해 영향을 받은 모든 사람들을 생각하고 있다'며 '믿음과 희망을 잃지 말아 달라. 여러분은 혼자가 아니다'라고 덧붙였다."
+texts = prompt_template.format(sentences)
+inputs = tokenizer(texts, return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=1024)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+- Prince William's wife Kate Middleton, 42, has been diagnosed with cancer after undergoing surgery for her abdominal pain, according to Reuters news agency. In an Instagram message on the 22nd (local time), Kate Middleton, the wife of Prince William, said that she was diagnosed with cancer after undergoing surgery for her abdominal pain in January and is currently undergoing chemical therapy. She said that the medical team recommended chemical therapy as a measure to prevent the spread of the disease, but that she and Prince William are trying to resolve the issue for their young family. She added that "The medical team recommended chemical therapy as a measure to prevent the spread of the disease.
+
+# example
+prompt_template = """다음 내용을 영어로 번역하세요.:
+{}
+
+번역:
+"""
+sentences = "애플이 주력 시장 중에 하나인 중국에서 현지 스마트폰 제조사들에게 밀리며 위기감이 증폭된 가운데 중국 소비자 잡기에 나서고 있다. 팀 쿡 CEO(최고경영자)가 직접 중국을 방문해 투자를 약속하고, '아이폰' 등 자사 기기에 중국 바이두의 AI(인공지능) 모델을 탑재하는 방안도 검토하고 있다. 중국 본토서 아이폰 할인 공세에 이어 전방위적 투자를 늘리는 모양새다."
+texts = prompt_template.format(sentences)
+inputs = tokenizer(texts, return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=1024)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+- With Apple becoming a target in China, a major market, the company is taking a stance in a Chinese consumer magazine. CEO Tim Cook is visiting China and is planning to invest, and is also considering adding Chinese Big Data AI models on Apple's products such as 'iPhone'. It seems that China is making a wide-ranging investment following the iPhone discounting wave on the mainland.
+```