Instructions to use cs-552-2026-camykaz/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs-552-2026-camykaz/math_model with Transformers:

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

pipe = pipeline("text-generation", model="cs-552-2026-camykaz/math_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-camykaz/math_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-camykaz/math_model", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cs-552-2026-camykaz/math_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs-552-2026-camykaz/math_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs-552-2026-camykaz/math_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs-552-2026-camykaz/math_model

SGLang

How to use cs-552-2026-camykaz/math_model 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 "cs-552-2026-camykaz/math_model" \
    --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": "cs-552-2026-camykaz/math_model",
		"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 "cs-552-2026-camykaz/math_model" \
        --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": "cs-552-2026-camykaz/math_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs-552-2026-camykaz/math_model with Docker Model Runner:
```
docker model run hf.co/cs-552-2026-camykaz/math_model
```

cyrineakrout commited on Jun 2

Commit

f5fbc77

verified ·

1 Parent(s): a861ee8

Patch v6 robust boxed-answer inference setup: tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +0 -1

tokenizer_config.json CHANGED Viewed

@@ -27,6 +27,5 @@
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null,
-  "chat_template": "{%- set boxed_instruction = \"You are a mathematical reasoning model. Solve the problem carefully. Use concise scratch work with only the essential intermediate steps. Return the final answer in exact form whenever possible. Put the final answer inside a LaTeX \\\\boxed{} expression. Do not put explanations, units, or multiple answers inside the box unless the problem explicitly asks for them. \" %}\n{%- if messages|length > 0 and messages[0]['role'] == 'system' %}\n    {%- set system_message = boxed_instruction + \"\\n\\n\" + messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = boxed_instruction %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}\n{%- for message in loop_messages %}\n    {{- '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>\\n' }}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}",
   "truncation_side": "left"
 }

   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null,
   "truncation_side": "left"
 }