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

Libraries

How to use modrill/code-think-o7b-20260908 with Transformers:

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

pipe = pipeline("text-generation", model="modrill/code-think-o7b-20260908")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("modrill/code-think-o7b-20260908")
model = AutoModelForCausalLM.from_pretrained("modrill/code-think-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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use modrill/code-think-o7b-20260908 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/code-think-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/code-think-o7b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/code-think-o7b-20260908

SGLang

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

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

code-think-o7b-20260908

File size: 1,400 Bytes

91ac68c

{"adapter_tree_sha256":"fe68ff152a282e7ce3e0a14738544921a839b859686c47a1a2593b7e3b8893c4","base_model_path":"/workspace/code-sft-infra/models/olmo-3-1025-7b","checkpoint_manifest_sha256":"42a14a7b08216555ed6f8d720039289212cc0607dfbcc7c9afefd8ad668411e4","checkpoint_path":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/arms/O7B-THINK/out/O7B-THINK/a81bae42db3975be1671e27b9c9a56da1a9f980f/olmo3-lcb-noprefill/2d7e9e7d85c88ad60cd12df874fd903f00c017cffe9990a8c6fb5f444642dbf3/step-000904-tokens-63378772","label":"v4-o7b-think","merge_backend":"merge_for_eval","merged_at_unix":1788900738.1913726,"merged_model_path":"/workspace/code-sft-runs/rstar-eval/official-dev256/v4-o7b-think/scratch/step-000904-tokens-63378772-merged-full","merged_tree_sha256":"29759f0db460ac44ed01c0cfc3a82b01a2897a24361e4a1553208bf0e726793f","receipt_sha256":"b928e8315517654284fcd886a7a1d747c732c48405275af9c37703f839e68117","schema":"CODE_SFT_OFFICIAL_DEV256_MERGE_RECEIPT_V1","token_rows_meta_path":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/arms/O7B-THINK/out/O7B-THINK/a81bae42db3975be1671e27b9c9a56da1a9f980f/olmo3-lcb-noprefill/2d7e9e7d85c88ad60cd12df874fd903f00c017cffe9990a8c6fb5f444642dbf3/step-000904-tokens-63378772/TOKEN_ROWS_META.json","token_rows_meta_worker":"rstar_dual_worker_v4","untied_export":{"lm_head_weight_shard":"model.safetensors","tie_word_embeddings":false}}