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

Libraries

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

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

pipe = pipeline("text-generation", model="cs-552-2026-the-transformers/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-the-transformers/math_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-the-transformers/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-the-transformers/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-the-transformers/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-the-transformers/math_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Automated MNLP evaluation report (2026-06-11)

by zechen-nlp - opened Jun 3

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

+12069

-62

initial commitda27515a

Upload math SFT checkpoint (smoke test)2b172d75

Upload math SFT checkpoint (smoke test)ed23471f

Upload math SFT checkpointf13b0a9e

Automated MNLP evaluation report (2026-05-23) (#1)b8bbbde1

Upload exp4b: SFT→DPO v2 (L3-5, ≤5/8, beta=0.1, lr=5e-7)32ac537f

Automated MNLP evaluation report (2026-05-27) (#2)4bd50478

Fix tokenizer_config.json: is_local=false362bfeb3

Fix README: add base_model, fix model references6af8d3ad

Push DPO checkpoint with T=0.3 (optimal for pass@8 on CI gate)ac3517ea

sft_mixlong_full: best Hard100 p@8, temperature=0.3a4211967

Automated MNLP evaluation report (2026-05-29) (#3)fab7629d

exp6: SFT(NuminaMath) -> DPO v2, T=0.35184a786

Automated MNLP evaluation report (2026-06-01) (#4)2af62977

Push exp8 GRPO best (step 750), gen temp=0.7 for pass@8ab2047d1

Automated MNLP evaluation report (2026-06-03)e7e68123

zechen-nlp

Jun 3

Posted by the course CI pipeline.

zechen-nlp changed pull request title from Automated MNLP evaluation report (2026-06-03) to Automated MNLP evaluation report (2026-06-05) Jun 5

Update Automated MNLP evaluation report (2026-06-05)8e99ddb9

Update Automated MNLP evaluation report (2026-06-05)a10f24c3

zechen-nlp changed pull request title from Automated MNLP evaluation report (2026-06-05) to Automated MNLP evaluation report (2026-06-06) Jun 6

Update Automated MNLP evaluation report (2026-06-06)6d259bb5

zechen-nlp changed pull request title from Automated MNLP evaluation report (2026-06-06) to Automated MNLP evaluation report (2026-06-08) Jun 8

Update Automated MNLP evaluation report (2026-06-08)0342b564

zechen-nlp changed pull request title from Automated MNLP evaluation report (2026-06-08) to Automated MNLP evaluation report (2026-06-09) Jun 9

Update Automated MNLP evaluation report (2026-06-09)18f2472d

zechen-nlp changed pull request title from Automated MNLP evaluation report (2026-06-09) to Automated MNLP evaluation report (2026-06-10) Jun 10

Update Automated MNLP evaluation report (2026-06-10)ba1321d1

zechen-nlp changed pull request title from Automated MNLP evaluation report (2026-06-10) to Automated MNLP evaluation report (2026-06-11) Jun 11

Update Automated MNLP evaluation report (2026-06-11)3c2440f9

Update Automated MNLP evaluation report (2026-06-11)31cbb7dc

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

README.md
chat_template.jinja
config.json
generation_config.json
model.safetensors
tokenizer_config.json

· Sign up or log in to comment