Instructions to use deepcogito/cogito-671b-v2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepcogito/cogito-671b-v2.1 with Transformers:

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

pipe = pipeline("text-generation", model="deepcogito/cogito-671b-v2.1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepcogito/cogito-671b-v2.1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepcogito/cogito-671b-v2.1", trust_remote_code=True)
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepcogito/cogito-671b-v2.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepcogito/cogito-671b-v2.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepcogito/cogito-671b-v2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepcogito/cogito-671b-v2.1

SGLang

How to use deepcogito/cogito-671b-v2.1 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 "deepcogito/cogito-671b-v2.1" \
    --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": "deepcogito/cogito-671b-v2.1",
		"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 "deepcogito/cogito-671b-v2.1" \
        --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": "deepcogito/cogito-671b-v2.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepcogito/cogito-671b-v2.1 with Docker Model Runner:
```
docker model run hf.co/deepcogito/cogito-671b-v2.1
```

Plans for smaller cogito v2.1

by ankandrew - opened Nov 21, 2025

Discussion

ankandrew

Nov 21, 2025

Hi, first thanks for the dedication and the great work. Are there plans to release smaller models i.e. 14B like you did for v1?

drishanarora

Deep Cogito org Nov 25, 2025

•

edited Nov 25, 2025

Thanks for the kind words! The larger run is already in progress. We should have it released soon!

ZiggyS

Nov 27, 2025

I agree, you guys are one the best out there, but for those of us that want to do it local and dont have unlimited GPU budgets, stuff like this is our of our reach.

ankandrew

Feb 9

•

edited Feb 9

Any updates on this @drishanarora ?

ankandrew changed discussion status to closed Mar 27

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