Instructions to use anonymous-2321/Think2SQL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anonymous-2321/Think2SQL-4B with Transformers:

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

pipe = pipeline("text-generation", model="anonymous-2321/Think2SQL-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anonymous-2321/Think2SQL-4B")
model = AutoModelForCausalLM.from_pretrained("anonymous-2321/Think2SQL-4B")
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 anonymous-2321/Think2SQL-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anonymous-2321/Think2SQL-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anonymous-2321/Think2SQL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anonymous-2321/Think2SQL-4B

SGLang

How to use anonymous-2321/Think2SQL-4B 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 "anonymous-2321/Think2SQL-4B" \
    --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": "anonymous-2321/Think2SQL-4B",
		"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 "anonymous-2321/Think2SQL-4B" \
        --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": "anonymous-2321/Think2SQL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anonymous-2321/Think2SQL-4B with Docker Model Runner:
```
docker model run hf.co/anonymous-2321/Think2SQL-4B
```

anonymous-2321 commited on Mar 5

Commit

f31305c

verified ·

1 Parent(s): 7a41394

Update chat_template.jinja

Browse files

Include Reasoning tokens by default when starting decoding.

Files changed (1) hide show

chat_template.jinja +5 -8

chat_template.jinja CHANGED Viewed

@@ -35,14 +35,14 @@
         {%- if message.reasoning_content is string %}
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
-            {%- if '</think>' in content %}
-                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
             {%- endif %}
         {%- endif %}
         {%- if loop.index0 > ns.last_query_index %}
             {%- if loop.last or (not loop.last and reasoning_content) %}
-                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
             {%- else %}
                 {{- '<|im_start|>' + message.role + '\n' + content }}
             {%- endif %}
@@ -82,8 +82,5 @@
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-    {%- if enable_thinking is defined and enable_thinking is false %}
-        {{- '<think>\n\n</think>\n\n' }}
-    {%- endif %}
 {%- endif %}

         {%- if message.reasoning_content is string %}
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
+            {%- if '</reasoning>' in content %}
+                {%- set reasoning_content = content.split('</reasoning>')[0].rstrip('\n').split('<reasoning>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</reasoning>')[-1].lstrip('\n') %}
             {%- endif %}
         {%- endif %}
         {%- if loop.index0 > ns.last_query_index %}
             {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<reasoning>\n' + reasoning_content.strip('\n') + '\n</reasoning>\n\n' + content.lstrip('\n') }}
             {%- else %}
                 {{- '<|im_start|>' + message.role + '\n' + content }}
             {%- endif %}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>\n\n</think>\n\n<reasoning>\n'}}
 {%- endif %}