Instructions to use modrill/math-nothink-o7b-20260908 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/math-nothink-o7b-20260908 with Transformers:

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

pipe = pipeline("text-generation", model="modrill/math-nothink-o7b-20260908")
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("modrill/math-nothink-o7b-20260908")
model = AutoModelForCausalLM.from_pretrained("modrill/math-nothink-o7b-20260908", 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 modrill/math-nothink-o7b-20260908 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/math-nothink-o7b-20260908"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/math-nothink-o7b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/math-nothink-o7b-20260908

SGLang

How to use modrill/math-nothink-o7b-20260908 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 "modrill/math-nothink-o7b-20260908" \
    --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": "modrill/math-nothink-o7b-20260908",
		"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 "modrill/math-nothink-o7b-20260908" \
        --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": "modrill/math-nothink-o7b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/math-nothink-o7b-20260908 with Docker Model Runner:
```
docker model run hf.co/modrill/math-nothink-o7b-20260908
```

math-nothink-o7b-20260908 / MERGE_RECEIPT.json

modrill

freeze: merged endpoint + LoRA adapter for modrill/nothink-src-o7b-20260908

4b08ae0 verified about 1 month ago

Raw History Blame Contribute Delete

690 Bytes

	{
	"schema": "q4b-think-b-2ep-merge-receipt/1",
	"arm": "O7B-NOTHINK-EP-X",
	"checkpoint": "/workspace/math_think_a3b2507_20260906/train_v3_eot_20260908/runs/O7B-NOTHINK-EP-X/train/checkpoint-update-00000175-tokens-000011441234",
	"device": "cuda:0",
	"dtype": "bfloat16",
	"adapter_config_sha256": "a37aa48d13618232c43abf0e86a19946114af9857c0748fa3714793257d1bbf1",
	"adapter_model_sha256": "f455b0193d3b8065e86b9cd31c5a61f234eaf795c1a60d0d3def1bee0da4aa89",
	"trainable_token_indices": {
	"embed_tokens": [
	100257
	],
	"lm_head": [
	100257
	]
	},
	"untied": true,
	"tokenizer_source": "/workspace/OLMO3-MATH-DUAL-v1/models/Olmo-3-1025-7B-996971efdc50"
	}