43 lines
1.6 KiB
Markdown
43 lines
1.6 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: other
|
||
|
|
license_name: gemma-terms-of-use
|
||
|
|
license_link: https://ai.google.dev/gemma/terms
|
||
|
|
language:
|
||
|
|
- ko
|
||
|
|
- en
|
||
|
|
tags:
|
||
|
|
- korean
|
||
|
|
- gemma
|
||
|
|
- pytorch
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
base_model: beomi/gemma-ko-2b
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# Gemma Ko 2B Instruct v0.51
|
||
|
|
|
||
|
|
- Eval Loss: `1.33753`
|
||
|
|
- Train Loss: `1.26453`
|
||
|
|
- lr: `1.5e-5`
|
||
|
|
- optimizer: adamw
|
||
|
|
- lr_scheduler_type: cosine
|
||
|
|
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
### Model Description
|
||
|
|
|
||
|
|
The Gemma Ko 2B Instruct v0.51 model is designed for generating human-like text in the Korean language.
|
||
|
|
It can be used for a variety of natural language processing tasks, such as language translation, text summarization, question answering, and conversation generation.
|
||
|
|
This model is particularly well-suited for applications that require high-quality, coherent, and contextually relevant Korean text generation.
|
||
|
|
|
||
|
|
- **Developed by:** `lemon-mint`
|
||
|
|
- **Model type:** Gemma
|
||
|
|
- **Language(s) (NLP):** Korean, English
|
||
|
|
- **License:** [gemma-terms-of-use](https://ai.google.dev/gemma/terms)
|
||
|
|
- **Finetuned from model:** [beomi/gemma-ko-2b](https://huggingface.co/beomi/gemma-ko-2b)
|
||
|
|
|
||
|
|
# Limitations and Ethical Considerations
|
||
|
|
|
||
|
|
As Gemma Ko 2B has been trained on extensive web data, biases present in the training data may be reflected in the model. Additionally, there is a possibility that it may generate sentences containing errors or incorrect information. Therefore, rather than blindly trusting the model's output, it is necessary to refer to it with caution.
|