--- license: llama2 datasets: - HuggingFaceH4/ultrachat_200k - HuggingFaceH4/ultrafeedback_binarized - HuggingFaceH4/cai-conversation-harmless language: - th - en --- # SambaLingo-Thai-Chat SambaLingo-Thai-Chat is a human aligned chat model trained in Thai and English. It is trained using direct preference optimization on top the base model [SambaLingo-Thai-Base](https://huggingface.co/sambanovasystems/SambaLingo-Thai-Base). The base model adapts [Llama 2](https://huggingface.co/meta-llama/Llama-2-7b-hf) to Thai by training on 63 billion tokens from the Thai split of the [Cultura-X](https://huggingface.co/datasets/uonlp/CulturaX) dataset. ## Model Description - **Developed by:** [SambaNova Systems](https://sambanova.ai/) - **Model type:** Language Model - **Language(s):** Thai, English - **Finetuned from model:** [Llama 2](https://huggingface.co/meta-llama/Llama-2-7b-hf) - **Blog Post**: Will be released soon! ## Getting Started ### Loading Model With Hugging Face Please make sure to set use_fast=False when loading the tokenizer. ```python from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/SambaLingo-Thai-Chat", use_fast=False) model = AutoModelForCausalLM.from_pretrained("sambanovasystems/SambaLingo-Thai-Chat", device_map="auto", torch_dtype="auto") ``` ### Interacting With Model Pipeline Please make sure to set use_fast=False when loading the tokenizer. ```python from transformers import pipeline pipe = pipeline("text-generation", model="sambanovasystems/SambaLingo-Thai-Chat", device_map="auto", use_fast=False) messages = [ {"role": "user", "content": {YOUR_QUESTION}}, ] prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipe(prompt)[0] outputs = outputs["generated_text"] ``` ### Suggested Inference Parameters - Temperature: 0.8 - Repetition penalty: 1.0 - Top-p: 0.9 ### Prompting Guidelines To prompt this model, please use the following chat template: ``` <|user|>:\n{question}\n<|assistant|>\n ``` ### Example Prompts and Generations ``` <|user|>: ปรัชญาทางเศรษฐกิจที่พระบาทสมเด็จพระมหาภูมิพลอดุลยเดชมหาราช บรมนาถบพิตรมีพระราชดำรัสแก่ชาวไทย มีชื่อว่าอะไร <|assistant|>: ปรัชญาทางเศรษฐกิจที่พระบาทสมเด็จพระปรมินทรมหาภูมิพลอดุลยเดชทรงมีพระราชดำรัสแก่ชาวไทยเรียกว่า "ปรัชญาเศรษฐกิจพอเพียง" ปรัชญานี้เน้นความสำคัญของการพัฒนาแบบองค์รวมแ ละความสมดุล โดยคำนึงถึงสภาพแวดล้อมทางสังคม เศรษฐกิจ และสิ่งแวดล้อม ปรัชญาเศรษฐกิจพอเพียงเน้นความสำคัญของการพึ่งพาตนเอง ความมีเหตุผล และการประหยัด ตลอดจนความสำคัญของก ารพัฒนาจิตใจและจิตวิญญาณ ปรัชญานี้เน้นย้ำถึงความสำคัญของการดำเนินชีวิตอย่างพอประมาณ มีเหตุผล และมีคุณธรรม ตลอดจนความสำคัญของการพัฒนาความรู้และทักษะอย่างต่อเนื่อง ปรัชญาเศรษฐกิ จพอเพียงได้รับการยกย่องอย่างกว้างขวางว่าเป็นแนวทางแก้ไขปัญหาการพัฒนาที่ยั่งยืนและเป็นแนวทางในการดำเนินชีวิตที่นำไปสู่ความสุขและความเป็นอยู่ที่ดี ``` ## Training Details The alignment phase follows the recipe for [Zephyr-7B](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), and comprises two stages: supervised fine-tuning (SFT) and Direct Performance Optimization (DPO). The SFT phase was done on the [ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset mixed with the Google translated version of the ultrachat_200k dataset. It was trained for one epoch with global batch size 512 and max sequence length 2048 tokens. We used a linear decay learning rate of 2e-5 and 10% warmup. The DPO phase was done on the [ultrafeedback](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) dataset and [cai-conversation-harmless](https://huggingface.co/datasets/HuggingFaceH4/cai-conversation-harmless) dataset, mixed with 10% of the data Google translated. It was trained with global batch size 32 and for three epochs. We used a linear decay learning rate of 5e-7, 10% warmup and β=0.1 as the regularization factor for DPO. ## Tokenizer Details We extended the vocabulary of the base llama model from 32,000 tokens to 57,000 tokens by adding up to 25,000 non-overlapping tokens from the new language. ## Uses ### Direct Use Use of this model is governed by the Meta’s [Llama 2 Community License Agreement](https://ai.meta.com/llama/license/). Please review and accept the license before downloading the model weights. ### Out-of-Scope Use SambaLingo should NOT be used for: - Mission-critical applications - Applications that involve the safety of others - Making highly important decisions ## Bias, Risks, and Limitations Like all LLMs, SambaLingo has certain limitations: - Hallucination: Model may sometimes generate responses that contain plausible-sounding but factually incorrect or irrelevant information. - Code Switching: The model might unintentionally switch between languages or dialects within a single response, affecting the coherence and understandability of the output. - Repetition: The Model may produce repetitive phrases or sentences, leading to less engaging and informative responses. - Coding and Math: The model's performance in generating accurate code or solving complex mathematical problems may be limited. - Toxicity: The model could inadvertently generate responses containing inappropriate or harmful content. ## Acknowledgments We extend our heartfelt gratitude to the open-source AI community; this endeavor would not have been achievable without open source. SambaNova embraces the open-source community and aspires to actively contribute to this initiative. We would like to give a special thanks to the following groups: - Meta for open sourcing LLama 2 and open sourcing FLORES-200 dataset - Nguyen et al for open sourcing CulturaX dataset - CohereAI for releasing AYA-101 and open sourcing a multilingual instruction tuning dataset - EleutherAI for their open source evaluation framework - Hugging Face-H4 team for open source the zephyr training recipe and alignment handbook repo ## Cite SambaLingo ``` @software{sambalingo, title = {{SambaLingo: Open Source Language Experts}}, author = {SambaNova Systems}, url = {https://huggingface.co/sambanovasystems/SambaLingo-Thai-Chat} month = {2}, year = {2024}, version = {1.0}, } ```