Instructions to use CohereLabs/North-Mini-Code-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/North-Mini-Code-1.0 with Transformers:

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

pipe = pipeline("text-generation", model="CohereLabs/North-Mini-Code-1.0")
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("CohereLabs/North-Mini-Code-1.0")
model = AutoModelForCausalLM.from_pretrained("CohereLabs/North-Mini-Code-1.0", 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 CohereLabs/North-Mini-Code-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/North-Mini-Code-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CohereLabs/North-Mini-Code-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CohereLabs/North-Mini-Code-1.0

SGLang

How to use CohereLabs/North-Mini-Code-1.0 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 "CohereLabs/North-Mini-Code-1.0" \
    --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": "CohereLabs/North-Mini-Code-1.0",
		"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 "CohereLabs/North-Mini-Code-1.0" \
        --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": "CohereLabs/North-Mini-Code-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CohereLabs/North-Mini-Code-1.0 with Docker Model Runner:
```
docker model run hf.co/CohereLabs/North-Mini-Code-1.0
```

Community docs proposal: North Mini Code typed-channel serving on Apple Silicon

#16

by Raullen - opened 4 days ago

Discussion

Raullen

4 days ago

Proposing a small community deployment note for clients that want to connect a local Mac inference server to a coding agent.

The relevant distinction is North Mini Code's typed-channel protocol. Rapid-MLX selects the cohere_command4 reasoning parser; its family default does not enable a tool parser. The parser tests cover full/streamed boundaries and JSON-shaped reasoning. A chat endpoint alone therefore should not be advertised as a qualified coding-agent tool backend.

Suggested scope: document checkpoint selection, /v1/models discovery and reasoning/content separation first. Tool-use documentation should require a separate round-trip test with the card's native tool history, including parsed arguments and replayed results. This would complement the card's vLLM examples without implying equivalent agent benchmark scores.

Concrete catalog entry: north-mini-code-4bit → mlx-community/North-Mini-Code-1.0-4bit@dfbe084dfa26e241345af99ca32848f38fd865f9. This is a conversion/distribution artifact; it is not presented as an official upstream release.

Source references (fixed Rapid commit): catalog, parser routing, typed-channel tests.

Verification status: this proposal is based on reading the catalog, implementation and the linked documentation/tests. No fresh model inference or test-suite run was performed for this submission; source tests are not an end-to-end qualification. It requests a community documentation scope, not an official endorsement or a performance listing.

Disclosure: I maintain Rapid-MLX. Prepared with AI assistance under my direction. Anonymous usage-metadata telemetry is enabled by default; DO_NOT_TRACK=1 disables it. The original model and conversion terms continue to apply.

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

Tap or paste here to upload images

· Sign up or log in to comment