WangchanX-Legal-ThaiCCL-Retriever

WangchanX-Legal-ThaiCCL-Retriever

This model card describes WangchanX-Legal-ThaiCCL-Retriever, a retriever model fine-tuned from the bge-m3 model on the WangchanX-Legal-ThaiCCL-RAG dataset. It is designed to retrieve relevant legal text sections in response to legal questions posed in Thai, specifically focusing on Corporate and Commercial Law (CCL).

Model Details:

• Base Model: bge-m3
• Fine-tuned Dataset: WangchanX-Legal-ThaiCCL-RAG dataset
• Language: Thai
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 1024 tokens
• License: MIT

WangchanX-Legal-ThaiCCL-RAG

This dataset focuses on supporting Thai legal question-answering systems using Retrieval-Augmented Generation (RAG), focusing on Corporate and Commercial Law.

Intended Use Cases: This model is designed for use as a retriever model within a larger RAG pipeline.

• Legal Question Answering: Serving as a core component in a larger question-answering system that provides answers to user queries about Thai law.
• Legal Information Retrieval: Enabling efficient retrieval of information from Thai legal texts.

<!-- ## Usage This model is designed for use as a retriever model within a larger RAG pipeline. Given a legal question in Thai, it will retrieve the most relevant sections from the Thai CCL corpus. You can integrate this model into your application using the Hugging Face Transformers library. --> <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> <!-- ## Citation ### BibTeX -->