Downloads · 30 days
1.4K
3% of all-time downloads
openthaigpt/openthaigpt-1.0.0-7b-chat
openthaigpt-1.0.0-7b-chat is a text generation model from openthaigpt. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama2.
Downloads · 30 days
1.4K
3% of all-time downloads
All-time downloads
40.9K
Public
Parameters
6.8B
31.4 GB on disk
Likes
18
Public
Click a slice to open those files.
.gguf17.8 GB · 57%
From the Hugging Face model README
🇹🇭 OpenThaiGPT 7b Version 1.0.0 is an advanced 7-billion-parameter Thai language chat model based on LLaMA v2 released on April 8, 2024. It has been specifically fine-tuned for Thai instructions and enhanced by incorporating over 10,000 of the most commonly used Thai words into the large language model's (LLM) dictionary, significantly boosting its response speed.
** Please take a look at OTG 7b (April 2024) for this model's evaluation result.
| Exams | OTG 7b (Aug 2023) | OTG 13b (Dec 2023) | <b style="color:blue">OTG 7b (April 2024)</b> | OTG 13b (April 2024) | OTG 70b (April 2024) | SeaLLM 7b v1 | SeaLLM 7b v2 | SeaLion 7b | WanchanGLM 7b | Sailor-7b-Chat | TyphoonGPT 7b Instruct | GPT3.5 | GPT4 | Gemini Pro | Gemini 1.5 | Claude 3 Haiku | Claude 3 Sonnet | Claude 3 Opus |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| A-Level | 17.50% | 34.17% | <b style="color:blue">25.00%</b> | 30.83% | 45.83% | 18.33% | 34.17% | 21.67% | 17.50% | 40.00% | 37.50% | 38.33% | 65.83% | 56.67% | 55.83% | 58.33% | 59.17% | 77.50% |
| TGAT | 24.00% | 22.00% | <b style="color:blue">22.00%</b> | 36.00% | 36.00% | 14.00% | 28.00% | 24.00% | 16.00% | 34.00% | 30.00% | 28.00% | 44.00% | 22.00% | 28.00% | 36.00% | 34.00% | 46.00% |
| TPAT1 | 22.50% | 47.50% | <b style="color:blue">42.50%</b> | 27.50% | 62.50% | 22.50% | 27.50% | 22.50% | 17.50% | 40.00% | 47.50% | 45.00% | 52.50% | 52.50% | 50.00% | 52.50% | 50.00% | 62.50% |
| thai_investment_consultant_exams | 8.00% | 28.00% | <b style="color:blue">76.00%</b> | 84.00% | 68.00% | 16.00% | 28.00% | 24.00% | 16.00% | 24.00% | 32.00% | 40.00% | 64.00% | 52.00% | 32.00% | 44.00% | 64.00% | 72.00% |
| facebook_beleble_tha_200 | 25.00% | 45.00% | <b style="color:blue">34.50%</b> | 39.50% | 70.00% | 13.50% | 51.00% | 27.00% | 24.50% | 63.00% | 51.50% | 50.00% | 72.50% | 65.00% | 74.00% | 63.50% | 77.00% | 90.00% |
| xcopa_th_200 | 45.00% | 56.50% | <b style="color:blue">49.50%</b> | 51.50% | 74.50% | 26.50% | 47.00% | 51.50% | 48.50% | 68.50% | 65.00% | 64.00% | 82.00% | 68.00% | 74.00% | 64.00% | 80.00% | 86.00% |
| xnli2.0_th_200 | 33.50% | 34.50% | <b style="color:blue">39.50%</b> | 31.00% | 47.00% | 21.00% | 43.00% | 37.50% | 33.50% | 16.00% | 20.00% | 50.00% | 69.00% | 53.00% | 54.50% | 50.00% | 68.00% | 68.50% |
| ONET M3 | 17.85% | 38.86% | <b style="color:blue">34.11%</b> | 39.36% | 56.15% | 15.58% | 23.92% | 21.79% | 19.56% | 21.37% | 28.03% | 37.91% | 49.97% | 55.99% | 57.41% | 52.73% | 40.60% | 63.87% |
| ONET M6 | 21.14% | 28.87% | <b style="color:blue">22.53%</b> | 23.32% | 42.85% | 15.09% | 19.48% | 16.96% | 20.67% | 28.64% | 27.46% | 34.44% | 46.29% | 45.53% | 50.23% | 34.79% | 38.49% | 48.56% |
| AVERAGE SCORE | 23.83% | 37.27% | <b style="color:blue;font-size:1.3em">38.40%</b> | 40.33% | 55.87% | 18.06% | 33.56% | 27.44% | 23.75% | 37.28% | 37.67% | 43.07% | 60.68% | 52.30% | 52.89% | 50.65% | 56.81% | 68.32% |
| Thai language multiple choice exams, Test on unseen test sets, Zero-shot learning. Benchmark source code and exams information: https://github.com/OpenThaiGPT/openthaigpt_eval |
(Updated on: 7 April 2024)
| Models | ENGLISH (M3EXAM) | THAI (M3EXAM) |
|---|---|---|
| <b style="color:blue">OTG-7b</b> | <b style="color:blue">40.92 %</b> | <b style="color:blue">25.14 %</b> |
| OTG-13b | 53.69 % | 36.49 % |
| OTG-70b | 72.58 %< | 48.29 % |
| GPT-3.5-turbo-0613* | - | 34.1 % |
| GPT-4-0613* | - | 56.0 % |
| More information: https://blog.float16.cloud/the-first-70b-thai-llm/ |
Source Code: License Apache Software License 2.0.<br> Weight: Research and Commercial uses.<br>
Prompt format is based on Llama2 with a small modification (Adding "###" to specify the context part)
<s>[INST] <<SYS>
{system_prompt}
<</SYS>>
{human_turn1}###{context_turn1} [/INST]{assistant_turn1}</s><s>{human_turn2}###{context_turn2} [/INST] ...
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
กรุงเทพมีพื้นที่เท่าไร่###กรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน [/INST]
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]ได้เลยค่ะ ส้มตำเป็นเมนูที่ทำง่ายและอร่อย มาเริ่มกันเลยนะคะ</s><s>เริ่มได้เลย [/INST]
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]ได้เลยค่ะ ส้มตำเป็นเมนูที่ทำง่ายและอร่อย มาเริ่มกันเลยนะคะ</s><s>เริ่มได้เลย [/INST]
ตำไทยเป็นเมนูที่ใครๆ ก็คุ้นเคย ด้วยรสชาติที่กลมกล่อม หวาน เปรี้ยว เค็ม เผ็ด ครบรส วันนี้เราจะมาทำส้มตำด้วยกันค่ะ สิ่งแรกที่ต้องมีคือเครื่องปรุงดังนี้
- มะละกอดิบ 1 ลูก
- กุ้งแห้ง 1/2 ถ้วย
- กระเทียม 3 กลีบ
- พริกขี้หนู 3 เม็ด
- น้ำตาลปี๊บ 1 ช้อนโต๊ะ
- น้ำปลา 2 ช้อนโต๊ะ
- มะนาว 1 ลูก
- งาขาวคั่ว 1/4 ถ้วย
วิธีทำมีดังนี้ค่ะ
1. เริ่มจากล้างมะละกอให้สะอาด แล้วใช้มีดปอกเปลือก เอาไส้ออก หั่นเป็นเส้นบางๆ เตรียมไว้
2. ตำกุ้งแห้งให้ละเอียด แล้วตักขึ้นพักไว้
3. ใช้ครกหินหรือเครื่องปั่น บดพริกขี้หนูกับกระเทียมให้ละเอียด
4. ใส่กุ้งแห้งที่ตำแล้วลงไปผสม ตามด้วยน้ำตาลปี๊บ น้ำปลา มะนาว และเส้นมะละกอ คลุกเคล้าให้เข้ากัน
5. ชิมรสให้ได้รสหวาน เปรี้ยว เค็ม เผ็ด จากนั้นตักขึ้นเสิร์ฟพร้อมผักสด อาทิ กะหล่ำปลี ถั่วงอก แครอท ผักบุ้ง</s><s>ขอบคุณครับ [/INST]
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
กรุงเทพมีพื้นที่เท่าไร่###กรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน [/INST]
กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม.</s><s>และประชากรล่ะ [/INST]
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Ensure CUDA is available
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Using device: {device}")
# Init Model
model_path="openthaigpt/openthaigpt-1.0.0-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.float16)
model.to(device)
# Prompt
prompt = "สวัสดีครับ OpenThaiGPT"
llama_prompt = f"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด<</SYS>>\n\n{prompt} [/INST]"
inputs = tokenizer.encode(llama_prompt, return_tensors="pt")
inputs = inputs.to(device)
# Generate
outputs = model.generate(inputs, max_length=512, num_return_sequences=1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Install VLLM (https://github.com/vllm-project/vllm)
Run server
python -m vllm.entrypoints.api_server --model /path/to/model --tensor-parallel-size num_gpus
curl --request POST \
--url http://localhost:8000/generate \
--header "Content-Type: application/json" \
--data '{"prompt": "<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด\n<</SYS>>\n\nอยากลดความอ้วนต้องทำอย่างไร [/INST]","use_beam_search": false, "temperature": 0.1, "max_tokens": 512, "top_p": 0.75, "top_k": 40, "frequency_penalty": 0.3 "stop": "</s>"}'
git clone https://github.com/ggerganov/llama.cpp.git \
&& cd llama.cpp \
&& make -j LLAMA_CUBLAS=1 CUDA_DOCKER_ARCH=all
./server -m /path/to/ggml-model-f16.gguf -c 3072 -ngl 81 -ts 1,1 --host 0.0.0.0
curl --location 'http://localhost:8000/completion' \
--header 'Content-Type: application/json' \
--data '{
"prompt":"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด friendly\n\n<<SYS>>\n\nอยากลดความอ้วนต้องทำอย่างไร [/INST]",
"max_tokens": 512,
"stop":"</s>"
}'
There are two ways to run on ollama
ollama create -f ./Modelfile
ollama run pacozaa/openthaigpt
| Number of Parameters | FP 16 bits | 8 bits (Quantized) | 4 bits (Quantized) | Example Graphic Card for 4 bits |
|---|---|---|---|---|
| 7b | 24 GB | 12 GB | 6 GB | Nvidia RTX 4060 8GB |
| 13b | 48 GB | 24 GB | 12 GB | Nvidia RTX 4070 16GB |
| 70b | 192 GB | 96 GB | 48 GB | Nvidia RTX 4090 24GB x 2 cards |
If OpenThaiGPT has been beneficial for your work, kindly consider citing it as follows:
@misc{yuenyong2024openthaigpt15thaicentricopen,
title={OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model},
author={Sumeth Yuenyong and Kobkrit Viriyayudhakorn and Apivadee Piyatumrong and Jillaphat Jaroenkantasima},
year={2024},
eprint={2411.07238},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2411.07238},
}
Yuenyong, S., Viriyayudhakorn, K., Piyatumrong, A., & Jaroenkantasima, J. (2024). OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model. arXiv [Cs.CL]. Retrieved from http://arxiv.org/abs/2411.07238
<i>Disclaimer: Provided responses are not guaranteed.</i>