Tsunami-0.5-7B-Instruct
TSUNAMI: Transformative Semantic Understanding and Natural Augmentation Model for Intelligence.
TSUNAMI full name was created by ChatGPT.
infomation
Tsunami-0.5-7B-Instruct is Thai Large Language Model that fine-tuned from Qwen2.5-7B around 60,000 rows in Thai-specific domain.
Prompt Template
This model uses ChatML
prompt template:
<|im_start|>system
{System}<|im_end|>
<|im_start|>user
{User}<|im_end|>
<|im_start|>assistant
{Assistant}
How to use
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "Tsunami-th/Tsunami-0.5-7B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "สวัสดีครับ"}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
inputs = tokenizer(text, return_tensors="pt")
inputs = inputs.to(model.device)
with torch.no_grad():
output = model.generate(**inputs, max_new_tokens=512)
response = tokenizer.decode(output[0, len(inputs['input_ids'][0]):], skip_special_tokens=True)
Author
- Pollakrit Lorprasertkul | [email protected]
- Tsunami-0.5-7B-Instruct is the version 0.5 that did not train on the whole dataset.
- Tsunami-1.0-7B-Instruct is coming soon.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 28.04 |
IFEval (0-Shot) | 74.00 |
BBH (3-Shot) | 36.14 |
MATH Lvl 5 (4-Shot) | 0.15 |
GPQA (0-shot) | 7.83 |
MuSR (0-shot) | 12.21 |
MMLU-PRO (5-shot) | 37.92 |
- Downloads last month
- 335
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Tsunami-th/Tsunami-0.5-7B-Instruct
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard74.000
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard36.140
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.150
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.830
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.210
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard37.920