Instructions to use cs-552-2026-4neurons/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs-552-2026-4neurons/math_model with Transformers:

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

pipe = pipeline("text-generation", model="cs-552-2026-4neurons/math_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-4neurons/math_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-4neurons/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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cs-552-2026-4neurons/math_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs-552-2026-4neurons/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-552-2026-4neurons/math_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs-552-2026-4neurons/math_model

SGLang

How to use cs-552-2026-4neurons/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-552-2026-4neurons/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-552-2026-4neurons/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-552-2026-4neurons/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-552-2026-4neurons/math_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs-552-2026-4neurons/math_model with Docker Model Runner:
```
docker model run hf.co/cs-552-2026-4neurons/math_model
```

math_model

Commit History

Update generation_config.json

976ffbb
verified

leonardamsler commited on Jun 9

Automated MNLP evaluation report (2026-06-08) (#3)

8dea74b

leonardamsler

zechen-nlp commited on Jun 8

Upload checkpoint-200 math model with patched math chat template

9b57663
verified

leonardamsler commited on Jun 6

Upload config

eb7275b
verified

leonardamsler commited on May 29

Upload Qwen3ForCausalLM

345e971
verified

leonardamsler commited on May 29

Upload config

ba962ae
verified

leonardamsler commited on May 27

Upload tokenizer

516ddfa
verified

leonardamsler commited on May 27

Upload Qwen3ForCausalLM

c892eed
verified

leonardamsler commited on May 27

Automated MNLP evaluation report (2026-05-27) (#2)

d0772fd

leonardamsler

zechen-nlp commited on May 27

Upload config

8c93a21
verified

leonardamsler commited on May 26

Upload tokenizer

60e2d48
verified

leonardamsler commited on May 26

Upload Qwen3ForCausalLM

052a59f
verified

leonardamsler commited on May 26

Upload merged simple-SFT math checkpoint

55995b9
verified

leonardamsler commited on May 23

Upload merged checkpoint for math model

dc4146c
verified

leonardamsler commited on May 20

Automated MNLP evaluation report (2026-05-18) (#1)

d19a428

leonardamsler

zechen-nlp commited on May 18

Updated system prompt

4fd8ea3
verified

leonardamsler commited on May 18

SFT with mixed dataset, 1 epoch

fb0924a
verified

leonardamsler commited on May 18

Upload merged checkpoint for math model

3feaf21
verified

leonardamsler commited on May 15

Embed math system prompt as default in chat template

e0e2b54
verified

leonardamsler commited on May 14

Upload folder using huggingface_hub

ac61e6b
verified

leonardamsler commited on May 14

Upload config

8ebea82
verified

nicolasteissier commited on May 11

Upload tokenizer

68a9463
verified

nicolasteissier commited on May 11

Upload Qwen3ForCausalLM

b57886e
verified

nicolasteissier commited on May 11

initial commit

a6c3390
verified

nicolasteissier commited on May 11

Commit History

Update generation_config.json 976ffbb verified

Automated MNLP evaluation report (2026-06-08) (#3) 8dea74b

Upload checkpoint-200 math model with patched math chat template 9b57663 verified

Upload config eb7275b verified

Upload Qwen3ForCausalLM 345e971 verified

Upload config ba962ae verified

Upload tokenizer 516ddfa verified

Upload Qwen3ForCausalLM c892eed verified

Automated MNLP evaluation report (2026-05-27) (#2) d0772fd

Upload config 8c93a21 verified

Upload tokenizer 60e2d48 verified

Upload Qwen3ForCausalLM 052a59f verified

Upload merged simple-SFT math checkpoint 55995b9 verified

Upload merged checkpoint for math model dc4146c verified

Automated MNLP evaluation report (2026-05-18) (#1) d19a428

Updated system prompt 4fd8ea3 verified

SFT with mixed dataset, 1 epoch fb0924a verified

Upload merged checkpoint for math model 3feaf21 verified

Embed math system prompt as default in chat template e0e2b54 verified

Upload folder using huggingface_hub ac61e6b verified

Upload config 8ebea82 verified

Upload tokenizer 68a9463 verified

Upload Qwen3ForCausalLM b57886e verified

initial commit a6c3390 verified

Update generation_config.json

976ffbb
verified

Automated MNLP evaluation report (2026-06-08) (#3)

8dea74b

Upload checkpoint-200 math model with patched math chat template

9b57663
verified

Upload config

eb7275b
verified

Upload Qwen3ForCausalLM

345e971
verified

Upload config

ba962ae
verified

Upload tokenizer

516ddfa
verified

Upload Qwen3ForCausalLM

c892eed
verified

Automated MNLP evaluation report (2026-05-27) (#2)

d0772fd

Upload config

8c93a21
verified

Upload tokenizer

60e2d48
verified

Upload Qwen3ForCausalLM

052a59f
verified

Upload merged simple-SFT math checkpoint

55995b9
verified

Upload merged checkpoint for math model

dc4146c
verified

Automated MNLP evaluation report (2026-05-18) (#1)

d19a428

Updated system prompt

4fd8ea3
verified

SFT with mixed dataset, 1 epoch

fb0924a
verified

Upload merged checkpoint for math model

3feaf21
verified

Embed math system prompt as default in chat template

e0e2b54
verified

Upload folder using huggingface_hub

ac61e6b
verified

Upload config

8ebea82
verified

Upload tokenizer

68a9463
verified

Upload Qwen3ForCausalLM

b57886e
verified

initial commit

a6c3390
verified