Cogito v2.1 - 671B MoE

The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under an open license for commercial use.

• Cogito v2.1 models are hybrid reasoning models. Each model can answer directly (standard LLM), or self-reflect before answering (like reasoning models).
• The LLMs are trained using Iterated Distillation and Amplification (IDA) - an scalable and efficient alignment strategy for superintelligence using iterative self-improvement.
• The models have been optimized for coding, STEM, instruction following, general helpfulness and tool calling capabilities.
• This model is trained in over 30 languages and supports a context length of 128k.

Evaluations

For detailed evaluations, please refer to the Blog Post.

Usage

This checkpoint is a 671B parameter Mixture of Experts model in BF16 format, consuming approximately 1.3 TB for parameters. You will need at least 8 B200s (1 node) or 16 H200s (2 nodes) to run this model. For serving on 8 H200s, use the quantized version: deepcogito/cogito-671b-v2.1-FP8.

To download and cache the model:

pip install transformers hf_transfer accelerate vllm
hf download deepcogito/cogito-671b-v2.1

With HuggingFace pipeline

import torch
from transformers import pipeline
model_id = "deepcogito/cogito-671b-v2.1"
pipe = pipeline("text-generation", model=model_id, model_kwargs={"dtype": "auto"}, device_map="auto")
messages = [
    {"role": "system", "content": "Always respond in 1-2 words."},
    {"role": "user", "content": "Who created you?"},
]
without reasoning
outputs = pipe(messages, max_new_tokens=512, tokenizer_encode_kwargs={"enable_thinking": False})
print(outputs[0]["generated_text"][-1])
{'role': 'assistant', 'content': 'Deep Cogito'}
with reasoning
outputs = pipe(messages, max_new_tokens=512, tokenizer_encode_kwargs={"enable_thinking": True})
print(outputs[0]["generated_text"][-1])
{'role': 'assistant', 'content': 'The question is asking about my creator. I know that I\'m Cogito, an AI assistant created by Deep Cogito, which is an AI research lab. The question is very direct and can be answered very briefly. Since the user has specified to always respond in 1-2 words, I should keep my answer extremely concise.\n\nThe most accurate 2-word answer would be "Deep Cogito" - this names the organization that created me without any unnecessary details. "Deep Cogito" is two words, so it fits the requirement perfectly.\n</think>\nDeep Cogito'}

With HuggingFace AutoModel

from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "deepcogito/cogito-671b-v2.1"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
messages = [
    {"role": "system", "content": "Always respond in 1-2 words."},
    {"role": "user", "content": "Who created you?"}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)
To enable reasoning, set enable_thinking=True above.

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(**model_inputs, max_new_tokens=512)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Tool Calling with HuggingFace

Cogito models support tool calling (single, parallel, multiple and parallel_multiple) both in standard and extended thinking mode.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "deepcogito/cogito-671b-v2.1"
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)
def get_current_temperature(location: str) -> float:
    """
    Get the current temperature at a location.
    
    Args:
        location: The location to get the temperature for, in the format "City, Country"
    Returns:
        The current temperature at the specified location in the specified units, as a float.
    """
    return 22.
def generate(messages):
    global tokenizer, model
    prompt = tokenizer.apply_chat_template(
        messages,
        tools=[get_current_temperature],
        tokenize=False,
        add_generation_prompt=True,
        enable_thinking=False,
    )
    # To enable reasoning, set enable_thinking=True above.
model_inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to(model.device)
generated_ids = model.generate(**model_inputs, max_new_tokens=512)
    generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)]
    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response
messages = [{"role": "user", "content": "whats the temperature in Paris?"}]
response = generate(messages)

This will result in the output -

<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>get_current_temperature

You can then generate text from this input as normal. If the model generates a tool call, you should add it to the chat like so:

and then call the tool and append the result, with the tool role, and After that, you can generate() again to let the model use the tool result in the chat:

This should result in the string -

With vLLM

To enable reasoning, set enable_thinking=True above.

Tool Calling with vLLM

License

Contact