Instructions to use newmindai/Mecellem-Qwen3-1.7B-TR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use newmindai/Mecellem-Qwen3-1.7B-TR with Transformers:

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

pipe = pipeline("text-generation", model="newmindai/Mecellem-Qwen3-1.7B-TR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("newmindai/Mecellem-Qwen3-1.7B-TR")
model = AutoModelForMultimodalLM.from_pretrained("newmindai/Mecellem-Qwen3-1.7B-TR")
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 Settings

vLLM

How to use newmindai/Mecellem-Qwen3-1.7B-TR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "newmindai/Mecellem-Qwen3-1.7B-TR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "newmindai/Mecellem-Qwen3-1.7B-TR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/newmindai/Mecellem-Qwen3-1.7B-TR

SGLang

How to use newmindai/Mecellem-Qwen3-1.7B-TR 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 "newmindai/Mecellem-Qwen3-1.7B-TR" \
    --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": "newmindai/Mecellem-Qwen3-1.7B-TR",
		"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 "newmindai/Mecellem-Qwen3-1.7B-TR" \
        --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": "newmindai/Mecellem-Qwen3-1.7B-TR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use newmindai/Mecellem-Qwen3-1.7B-TR with Docker Model Runner:
```
docker model run hf.co/newmindai/Mecellem-Qwen3-1.7B-TR
```

Add library_name and links to paper and GitHub

by nielsr HF Staff - opened Jan 27

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+11

-6

Files changed (1) hide show

README.md +11 -6

README.md CHANGED Viewed

@@ -1,8 +1,11 @@
 ---
 language:
 - tr
 - en
 license: apache-2.0
 tags:
 - text-generation
 - turkish
@@ -14,14 +17,18 @@ tags:
 - continual-pretraining
 - TRUBA
 - MN5
-base_model: Qwen/Qwen3-1.7B
-pipeline_tag: text-generation
 ---
 # Mecellem-Qwen3-1.7B-TR
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 ## Model Description
 Mecellem-Qwen3-1.7B-TR is a Turkish legal language model adapted through Continual Pre-training (CPT) on Turkish legal and official texts. The model is based on Qwen3-1.7B decoder architecture (1.7B parameters) and trained using a four-phase curriculum learning strategy specifically designed to account for Turkish linguistic complexity. The CPT process progressively transitions from general-purpose texts to domain-specific legal content, achieving 36.2% perplexity reduction on Turkish legal text compared to the base Qwen3-1.7B model.
@@ -237,7 +244,7 @@ If you use this model, please cite our paper:
 ```bibtex
 @article{mecellem2026,
   title={Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain},
-  author={Uğur, Özgür and Göksu, Mahmut and Çimen, Mahmut and Yılmaz, Musa and Şavirdi, Esra and Demir, Alp Talha and Güllüce, Rumeysa and Çetin, İclal and Sağbaş, Ömer Can},
   journal={arXiv preprint arXiv:2601.16018},
   year={2026},
   month={January},
@@ -257,6 +264,4 @@ If you use this model, please cite our paper:
   journal={arXiv preprint arXiv:2409.00000},
   year={2024}
 }
-```
-<!-- Updated: 2026-01-15 09:38:29 -->

 ---
+base_model: Qwen/Qwen3-1.7B
 language:
 - tr
 - en
 license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
 tags:
 - text-generation
 - turkish
 - continual-pretraining
 - TRUBA
 - MN5
 ---
 # Mecellem-Qwen3-1.7B-TR
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+Mecellem-Qwen3-1.7B-TR is a Turkish legal language model presented in [Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain](https://huggingface.co/papers/2601.16018).
+**Resources:**
+- **Code:** [GitHub Repository](https://github.com/newmindai/mecellem-models)
+- **Paper:** [arXiv:2601.16018](https://arxiv.org/abs/2601.16018)
 ## Model Description
 Mecellem-Qwen3-1.7B-TR is a Turkish legal language model adapted through Continual Pre-training (CPT) on Turkish legal and official texts. The model is based on Qwen3-1.7B decoder architecture (1.7B parameters) and trained using a four-phase curriculum learning strategy specifically designed to account for Turkish linguistic complexity. The CPT process progressively transitions from general-purpose texts to domain-specific legal content, achieving 36.2% perplexity reduction on Turkish legal text compared to the base Qwen3-1.7B model.
 ```bibtex
 @article{mecellem2026,
   title={Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain},
+  author={Uğur, Özgür and Göksu, Mahmut and Çimen, Mahmut and Yılmaz, Musa and Şavirdi, Esra and Demir, Alp Talha and Güllüce, Rumeysa and İclal Çetin and Sağbaş, Ömer Can},
   journal={arXiv preprint arXiv:2601.16018},
   year={2026},
   month={January},
   journal={arXiv preprint arXiv:2409.00000},
   year={2024}
 }
+```