Update README.md

README.md

@@ -1,202 +1,80 @@
 ---
-base_model: unsloth/gemma-2-27b-bnb-4bit
+license: gemma
+datasets:
+- lmg-anon/VNTL-v3.1-1k
+- lmg-anon/VNTL-Chat
+language:
+- ja
+- en
 library_name: peft
+base_model: google/gemma-2-27b
+pipeline_tag: translation
 ---
 
-# 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]
-
-## 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 0.11.1
+# Summary
+
+This is a [Gemma 2 27B](https://huggingface.co/google/gemma-2-27b) qlora trained using a slightly modified version of the [VNTL-v3.1-1k](https://huggingface.co/datasets/lmg-anon/VNTL-v3.1-1k) dataset, concatenated with the [VNTL-Chat](https://huggingface.co/datasets/lmg-anon/VNTL-Chat) dataset. 
+
+This was trained mostly with the same hyperparameters as the [VNTL LLaMA 3 8B qlora](https://huggingface.co/lmg-anon/vntl-llama3-8b-qlora), the differences are:
+- Changed batch size and gradient accumulation from 6/5 to 15/2, this was done mostly for training efficiency since this qlora was trained using an A100.
+
+As the 8B qlora, this version also includes the "chat mode" for Japanese grammar questions.
+
+## Translation Prompt
+
+This is a prompt example for translation:
+```
+<<METADATA>>
+[character] Name: Uryuu Sakuno (瓜生 桜乃) | Gender: Female
+[character] Name: Uryuu Shingo (瓜生 新吾) | Gender: Male | Aliases: Onii-chan (お兄ちゃん)
+<<TRANSLATE>>
+<<JAPANESE>>
+買い物に行ったっきりなかなか帰ってこないと思ったら、やっぱり、迷子になっていたらしい。
+<<ENGLISH>>
+I thought she was taking too long to come back from shopping, and it turns out she had gotten lost as I expected.<eos>
+<<JAPANESE>>
+[新吾]: 「そっか。うん、電話してみてよかった」
+<<ENGLISH>>
+[Shingo]: "Is that so? Well, I'm glad I called you then."<eos>
+<<JAPANESE>>
+彼女は基本的に落ち着いた頭のいい子なんだけど、結構な筋金の入った方向音痴でもある。
+<<ENGLISH>>
+She's basically a smart and level-headed girl, but she also has a very bad sense of direction.<eos>
+<<JAPANESE>>
+頻度こそさほどではないものの、ひとたび迷子になると、とにかく派手に道に迷ってしまう。
+<<ENGLISH>>
+Though not very frequently, once she gets lost, she gets lost in a spectacular way.<eos>
+<<JAPANESE>>
+[桜乃]: 『……ごめん』
+<<ENGLISH>>
+[Sakuno]: "... Sorry."<eos>
+<<JAPANESE>>
+[新吾]: 「ううん、こう言っちゃなんだけど、迷子でよかったよ。 桜乃は可愛いから、いろいろ心配しちゃってたんだぞ俺」
+<<ENGLISH>>
+```
+
+The generated translation for that prompt, with temperature 0, is:
+```
+[Shingo]: "No, it's fine. I'm glad you got lost, actually. You're so cute, I was worried about you."
+```
+
+## Chat Prompt
+
+This is a prompt example for chat:
+```
+<<CHAT>>
+<<HUMAN>>
+Hi! Can you break down this sentence for me? Like, what is the meaning of "桜乃は可愛いから"?
+"ううん、こう言っちゃなんだけど、迷子でよかったよ。桜乃は可愛いから、いろいろ心配しちゃってたんだぞ俺」"
+<<LLM>>
+```
+
+The generated response for that prompt, with temperature 0, is:
+```
+Certainly! Let's start with your first question. "桜乃は可愛いから" is a phrase that consists of three parts:
+1. "桜乃" is a proper noun, likely a person's name.
+2. "は" is a particle that marks the topic of the sentence, in this case, "桜乃."
+3. "可愛い" is an adjective that means "cute" or "adorable."
+4. "から" is a conjunction that indicates a reason or cause.
+So, the literal translation of "桜乃は可愛いから" would be "Because Sakura is cute." It suggests that the speaker is about to provide a reason or explanation based on the fact that the person named Sakura is cute.
+```