Instructions to use JungZoona/T3Q-qwen2.5-14b-v1.0-e3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JungZoona/T3Q-qwen2.5-14b-v1.0-e3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="JungZoona/T3Q-qwen2.5-14b-v1.0-e3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JungZoona/T3Q-qwen2.5-14b-v1.0-e3")
model = AutoModelForCausalLM.from_pretrained("JungZoona/T3Q-qwen2.5-14b-v1.0-e3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use JungZoona/T3Q-qwen2.5-14b-v1.0-e3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JungZoona/T3Q-qwen2.5-14b-v1.0-e3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JungZoona/T3Q-qwen2.5-14b-v1.0-e3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JungZoona/T3Q-qwen2.5-14b-v1.0-e3

SGLang

How to use JungZoona/T3Q-qwen2.5-14b-v1.0-e3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "JungZoona/T3Q-qwen2.5-14b-v1.0-e3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JungZoona/T3Q-qwen2.5-14b-v1.0-e3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "JungZoona/T3Q-qwen2.5-14b-v1.0-e3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JungZoona/T3Q-qwen2.5-14b-v1.0-e3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JungZoona/T3Q-qwen2.5-14b-v1.0-e3 with Docker Model Runner:
```
docker model run hf.co/JungZoona/T3Q-qwen2.5-14b-v1.0-e3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Update @ 2025.03.14: The updated version, T3Q-qwen2.5-14b-v1.2-e2 release

Model Summary

T3Q-qwen2.5-14b-v1.0-e3 is a post-trained version of the Qwen/Qwen2.5-14B-Instruct-1M model.
(LoRA-8-4-0.0001-cosine-32-16 with train_data_v1.0)

Global Open LLM Leaderboard Performance

This model achieved 1st place in performance among models under 32b in the Global Open LLM Leaderboard. [View Article]

Page Capture

Quick Start

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "JungZoona/T3Q-qwen2.5-14b-v1.0-e3"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]