Downloads · 30 days
3
3% of all-time downloads
Konthee/Qwen3-32B-mt-medical-ch-th
Qwen3-32B-mt-medical-ch-th is a text generation model from Konthee. Use it when you need the model to write or continue text. It is set up for transformers.
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advance…
Downloads · 30 days
3
3% of all-time downloads
All-time downloads
100
Public
Parameters
32.8B
65.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors65.5 GB · 100%
From the Hugging Face model README
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Qwen3-32B has the following features:
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers.
With transformers<4.51.0, you will encounter the following error:
KeyError: 'qwen3'
The following contains a code snippet illustrating how to use the model generate content based on given inputs.
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Konthee/Qwen3-mt-medical-ch-th"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
# prepare the model input
system_prompt ="""\
You are a professional Chinese-Thai medical translator.
**Input**
You will be given two items:
Context — a short Chinese patient-doctor conversation.
Source — one specific Chinese sentence from that conversation to translate.
**Task**
Translate the Source sentence into Thai.
**Requirements**
1. Preserve the sentence’s medical meaning, tone, and intent.
2. Make the Thai sound natural and suitable for spoken dialogue between doctor and patient.
3.Ensure the translation is accurate, clear, and easy to understand.
**Output**
Provide only the final Thai translation. Do not include explanations, reasoning, or any additional text.
"""
user_prompt = """\
context : {}
source : {}
"""
messages = [
{"role": "user", "content": system_prompt}
{"role": "user", "content": user_prompt.format(context,source)},
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
# parsing thinking content
try:
# rindex finding 151668 (</think>)
index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content)
print("content:", content)
Results retrieved from the AI Benchmark 2025 MT Leaderboard https://benchmark.ai.in.th/score/leaderboard/2025-mt
| Split | BLEU score |
|---|---|
| public | 48.78 |
| private | 47.95 |
Data sourced directly from the leaderboard metrics
This model corresponds to team 220_อย่าคับ เจนมันเวิ่นเว้อป่าวว, which secured 1st place on both the public leaderboards in the 2025-QA competition on round 1
AI Thailand Benchmark Programs. (2025). 2025-MT: Machine Translation Task. Retrieved June 23, 2025, from https://benchmark.ai.in.th/task/detail/2025-mt