Instructions to use Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/models/Qwen3-0.6B-Base")
model = PeftModel.from_pretrained(base_model, "Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base")

Transformers

How to use Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base with Transformers:

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

pipe = pipeline("text-generation", model="Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base

SGLang

How to use Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base 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 "Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base" \
    --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": "Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base",
		"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 "Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base" \
        --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": "Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base with Docker Model Runner:
```
docker model run hf.co/Derinhelm/SyntaxQwen3-0.6-SynTagRusGRCT-Base
```

Derinhelm commited on Oct 25, 2025

Commit

bdf4cd8

verified ·

1 Parent(s): 8ceb41f

Upload 11 files

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -3,7 +3,7 @@ base_model: Qwen/Qwen3-0.6B-Base
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:/models/Qwen3-0.6B-Base
 - lora
 - transformers
 ---

 library_name: peft
 pipeline_tag: text-generation
 tags:
+- base_model:adapter:/Qwen/Qwen3-0.6B-Base
 - lora
 - transformers
 ---