kobkrit's picture
Update README.md
2bf0d3a verified
|
raw
history blame
No virus
17.8 kB
metadata
license: apache-2.0
language:
  - th
  - en
library_name: transformers
pipeline_tag: text-generation
tags:
  - openthaigpt
  - llama

🇹🇭 OpenThaiGPT 7b 1.0.0

OpenThaiGPT
More Info

🇹🇭 OpenThaiGPT 7b Version 1.0.0 is an advanced 7-billion-parameter Thai language chat model based on LLaMA v2. 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.

Highlights

  • Leading-edge Thai language LLM, setting new benchmarks by achieving the highest average scores across 9 Thai language evaluations when compared to all other open-source Thai LLMs.
  • Support for extended conversations across multiple turns.
  • Integration of Retrieval Augmented Generation (RAG) for enriched response generation.
  • Generation speeds increased by tenfold, thanks to the addition of 10,000 frequently used Thai words to the model's dictionary.
  • Built upon a foundation of more than 65 billion Thai language words and meticulously fine-tuned with over 1 million Thai instruction examples.
  • Capable of understanding and processing input contexts of up to 4096 Thai words, allowing for detailed and complex instructions.

Benchmark by OpenThaiGPT Eval

** Please take a look at OTG 7b (March 2024) for this model's evaluation result.

Exams OTG 7b (Aug 2023) OTG 13b (Dec 2023) OTG 7b (March 2024) OTG 13b (March 2024) OTG 70b (March 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% 25.00% 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% 22.00% 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% 42.50% 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%
Investment Consultant 8.00% 28.00% 76.00% 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 Belebele Thai 25.00% 45.00% 34.50% 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% 49.50% 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% 39.50% 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% 34.11% 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% 22.53% 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% 38.40% 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%

Benchmark Configuration

Licenses

Source Code: License Apache Software License 2.0.
Weight: Research and Commercial uses.

Sponsors

Supports

Prompt Format

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] ...

Practically, when usually used "\n" for a new line so,

<s>[INST] <<SYS>\n{system_prompt}\n<</SYS>>\n\n{human_turn1}###{context_turn1} [/INST]{assistant_turn1}</s><s>{human_turn2}###{context_turn2} [/INST] ...

System prompt:

You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด

Examples

Single Turn Conversation Example

<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>

สวัสดีครับ [/INST]

Single Turn Conversation with Context (RAG) Example

<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]

Multi Turn Conversation Example

First turn
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>

สวัสดีครับ [/INST]
Second turn
<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]
Third turn
<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]
Fourth turn
<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]

Multi Turn Conversation with Context (RAG) Example

<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]

How to use

Huggingface

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))

vLLM Engine for float16 model

  1. install VLLM (https://github.com/vllm-project/vllm)
  2. python -m vllm.entrypoints.api_server --model /path/to/model --tensor-parallel-size num_gpus
  3. run inference (CURL example)
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>"}'

LlamaCPP Engine for 4 bit model

Authors

Disclaimer: Provided responses are not guaranteed.