Update README.md

README.md

@@ -2,199 +2,136 @@
 library_name: transformers
 tags:
 - unsloth
+- KoAlpaca
+- Solar-Ko
+license: apache-2.0
+datasets:
+- beomi/KoAlpaca-RealQA
+language:
+- ko
+base_model:
+- beomi/Solar-Ko-Recovery-11B
+pipeline_tag: text-generation
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
+# KoAlpaca-RealQA-Solar-Ko-Recovery-11B (QLoRA with Unsloth)
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **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]
-
-## 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
+- **Developed by:** Lee Junbum (Beomi)
+- **Model type:** Instruction Tuned, with beomi/KoAlpaca-RealQA dataset
+- **Language(s) (NLP):** Korean Mainly, partially English
+- **License:** Apache 2.0
+- **Finetuned from model:** beomi/Solar-Ko-Recovery-11B
 
-[More Information Needed]
+### Model Sources
 
-#### Summary
+- **Training Code (Google Colab, Pro+ A100 40G):** https://colab.research.google.com/drive/11Ni8rOBmV1Qh15i7gMWncKjYBEdrJLBt
+- **Inference Code (Google Colab):** https://colab.research.google.com/drive/1hEPSHI4aGOn29Y21c6SWJc-y2ECVx3Bz?usp=sharing
 
+### Direct Use with Unsloth
 
+```python
+# pip install -U hf_transfer unsloth
+import os
 
-## Model Examination [optional]
+os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1" # download speed upto 1000MB/s
 
-<!-- Relevant interpretability work for the model goes here -->
+import torch
+from unsloth import FastLanguageModel
+from transformers import TextStreamer
 
-[More Information Needed]
 
-## Environmental Impact
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "beomi/KoAlpaca-RealQA-Solar-Ko-Recovery-11B", # YOUR MODEL YOU USED FOR TRAINING
+    max_seq_length = 2048,
+    dtype = torch.bfloat16,
+    load_in_4bit = True,
+)
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
-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).
+### Instruction:
+{}
 
-- **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]
+### Response:
+{}"""
 
-## Technical Specifications [optional]
+def gen(x):
+    inputs = tokenizer(
+    [
+        alpaca_prompt.format(
+            x.strip(), # instruction
+            "", # output - leave this blank for generation!
+        )
+    ], return_tensors = "pt").to("cuda")
 
-### Model Architecture and Objective
+    text_streamer = TextStreamer(tokenizer)
+    _ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 512)
+```
 
-[More Information Needed]
+### Generation Example
 
-### Compute Infrastructure
+**Sample 01**
 
-[More Information Needed]
+```
+gen("안녕하세요")
+```
 
-#### Hardware
+```
+<s> Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
-[More Information Needed]
+### Instruction:
+안녕하세요
 
-#### Software
+### Response:
+안녕하세요! 어떻게 도와드릴까요?</s>
+```
 
-[More Information Needed]
+**Sample 02**
 
-## Citation [optional]
+```
+gen("""아래 글을 한국어로 번역해줘.
+Dataset Summary
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+The KoAlpaca-RealQA dataset is a unique Korean instruction dataset designed to closely reflect real user interactions in the Korean language. Unlike conventional Korean instruction datasets that rely heavily on translated prompts, this dataset is composed of authentic Korean instructions derived from real-world use cases. Specifically, the dataset has been curated from user interactions with the ChatKoAlpaca service, which is based on the KoAlpaca model trained between 2023 and 2024.
 
-**BibTeX:**
+This dataset provides a more accurate portrayal of typical Korean user behaviors, questions, and language structures, making it highly relevant for developing language models aimed at understanding and responding to Korean speakers. By leveraging GPT4o to generate high-quality answers, KoAlpaca-RealQA aims to offer a robust resource for training models that need to engage with Korean users in a natural and meaningful way.
+""")
+```
 
-[More Information Needed]
+```
+<s> Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
-**APA:**
+### Instruction:
+아래 글을 한국어로 번역해줘.
+Dataset Summary
 
-[More Information Needed]
+The KoAlpaca-RealQA dataset is a unique Korean instruction dataset designed to closely reflect real user interactions in the Korean language. Unlike conventional Korean instruction datasets that rely heavily on translated prompts, this dataset is composed of authentic Korean instructions derived from real-world use cases. Specifically, the dataset has been curated from user interactions with the ChatKoAlpaca service, which is based on the KoAlpaca model trained between 2023 and 2024.
 
-## Glossary [optional]
+This dataset provides a more accurate portrayal of typical Korean user behaviors, questions, and language structures, making it highly relevant for developing language models aimed at understanding and responding to Korean speakers. By leveraging GPT4o to generate high-quality answers, KoAlpaca-RealQA aims to offer a robust resource for training models that need to engage with Korean users in a natural and meaningful way.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+### Response:
+KoAlpaca-RealQA 데이터셋은 한국어 사용자들의 실제 상호작용을 매우 잘 반영하도록 설계된 독특한 한국어 지시 데이터셋입니다. 번역된 프롬프트에 크게 의존하는 기존의 한국어 지시 데이터셋과 달리, 이 데이터셋은 실제 사용 사례에서 유래된 진정한 한국어 지시로 구성되어 있습니다. 특히, 이 데이터셋은 2023년과 2024년 사이에 훈련된 KoAlpaca 모델을 기반으로 한 ChatKoAlpaca 서비스와의 사용자 상호작용에서 수집되었습니다.
 
-[More Information Needed]
+이 데이터셋은 일반적인 한국어 사용자의 행동, 질문 및 언어 구조를 더 정확하게 묘사하여, 한국어 사용자를 이해하고 응답하는 언어 모델을 개발하는 데 매우 유용합니다. GPT4o를 활용하여 고품질의 답변을 생성함으로써, KoAlpaca-RealQA는 자연스럽고 의미 있는 방식으로 한국어 사용자와 상호작용해야 하는 모델을 훈련시키기 위한 강력한 자원을 목표로 하고 있습니다.</s>
+```
 
-## More Information [optional]
+**Sample 03**
 
-[More Information Needed]
+```
+gen("""KoAlpaca에 대해 설명해줘.""")
+```
 
-## Model Card Authors [optional]
+```
+<s> Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 
-[More Information Needed]
+### Instruction:
+KoAlpaca에 대해 설명해줘.
 
-## Model Card Contact
+### Response:
+KoAlpaca는 한국어 자연어 처리(NLP) 모델로, OpenAI의 GPT-3와 같은 대형 언어 모델(LLM)을 기반으로 합니다. KoAlpaca는 한국어 데이터를 주로 사용하여 학습되었기 때문에 한국어 텍스트를 이해하고 생성하는 데 특화되어 있습니다. 이 모델은 다양한 한국어 응용 프로그램에서 활용될 수 있으며, 예를 들어 대화형 AI, 번역, 요약, 질문 답변 등 여러 분야에서 사용될 수 있습니다.
 
-[More Information Needed]
+KoAlpaca는 한국어 사용자에게 보다 자연스럽고 유창한 언어 상호작용을 제공하며, 한국어 문맥을 잘 이해하고 처리할 수 있도록 설계되었습니다. 이러한 모델은 한국어 NLP 연구와 산업에서 중요한 도구로 사용될 수 있습니다.</s>
+```