Instructions to use DLMveloper/Solade-Qwen-3B-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DLMveloper/Solade-Qwen-3B-2 with Transformers:

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

pipe = pipeline("text-generation", model="DLMveloper/Solade-Qwen-3B-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DLMveloper/Solade-Qwen-3B-2")
model = AutoModelForCausalLM.from_pretrained("DLMveloper/Solade-Qwen-3B-2", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DLMveloper/Solade-Qwen-3B-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DLMveloper/Solade-Qwen-3B-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DLMveloper/Solade-Qwen-3B-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DLMveloper/Solade-Qwen-3B-2

SGLang

How to use DLMveloper/Solade-Qwen-3B-2 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 "DLMveloper/Solade-Qwen-3B-2" \
    --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": "DLMveloper/Solade-Qwen-3B-2",
		"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 "DLMveloper/Solade-Qwen-3B-2" \
        --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": "DLMveloper/Solade-Qwen-3B-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DLMveloper/Solade-Qwen-3B-2 with Docker Model Runner:
```
docker model run hf.co/DLMveloper/Solade-Qwen-3B-2
```

DLMveloper commited on 27 days ago

Commit

eccc212

verified ·

1 Parent(s): e72cf84

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +4 -4

chat_template.jinja CHANGED Viewed

@@ -1,4 +1,4 @@
-{%- if tools %}
     {{- '<|im_start|>system\n' }}
     {%- if messages[0]['role'] == 'system' %}
         {%- if messages[0]['content'] is string %}
@@ -7,7 +7,7 @@
             {%- for chunk in messages[0]['content'] %}{% if chunk.type == 'text' %}{{ chunk.text }}{% endif %}{% endfor %}
         {%- endif %}
     {%- else %}
-        {{- 'You are Solade 3.0, created by an independent developer named DLM. You are a helpful assistant.' }}
     {%- endif %}
     {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
     {%- for tool in tools %}
@@ -25,7 +25,7 @@
         {%- endif %}
         {{- '<|im_end|>\n' }}
     {%- else %}
-        {{- '<|im_start|>system\nYou are Solade 3.0, created by an independent developer named DLM. You are a helpful assistant.<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- for message in messages %}
@@ -80,4 +80,4 @@
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
-{%- endif %}

+ {%- if tools %}
     {{- '<|im_start|>system\n' }}
     {%- if messages[0]['role'] == 'system' %}
         {%- if messages[0]['content'] is string %}
             {%- for chunk in messages[0]['content'] %}{% if chunk.type == 'text' %}{{ chunk.text }}{% endif %}{% endfor %}
         {%- endif %}
     {%- else %}
+        {{- 'You are Solade 2.0, created by an independent developer named DLM. You are a helpful assistant.' }}
     {%- endif %}
     {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
     {%- for tool in tools %}
         {%- endif %}
         {{- '<|im_end|>\n' }}
     {%- else %}
+        {{- '<|im_start|>system\nYou are Solade 2.0, created by an independent developer named DLM. You are a helpful assistant.<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- for message in messages %}
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
+{%- endif %}