Instructions to use deepcogito/cogito-v1-preview-llama-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepcogito/cogito-v1-preview-llama-70B with Transformers:

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

pipe = pipeline("text-generation", model="deepcogito/cogito-v1-preview-llama-70B")
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("deepcogito/cogito-v1-preview-llama-70B")
model = AutoModelForCausalLM.from_pretrained("deepcogito/cogito-v1-preview-llama-70B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepcogito/cogito-v1-preview-llama-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepcogito/cogito-v1-preview-llama-70B"
# 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-v1-preview-llama-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepcogito/cogito-v1-preview-llama-70B

SGLang

How to use deepcogito/cogito-v1-preview-llama-70B 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-v1-preview-llama-70B" \
    --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-v1-preview-llama-70B",
		"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-v1-preview-llama-70B" \
        --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-v1-preview-llama-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepcogito/cogito-v1-preview-llama-70B with Docker Model Runner:
```
docker model run hf.co/deepcogito/cogito-v1-preview-llama-70B
```

drishanarora commited on Apr 8, 2025

Commit

1d624e2

verified ·

1 Parent(s): f4b2aa2

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -0

README.md CHANGED Viewed

@@ -23,8 +23,21 @@ The Cogito LLMs are instruction tuned generative models (text in/text out). All
   - In both standard and reasoning modes, Cogito v1-preview models outperform their size equivalent counterparts on common industry benchmarks.
 - Each model is trained in over 30 languages and supports a context length of 128k.
 For detailed evaluations, please refer to the [Blog Post](https://www.deepcogito.com/research/cogito-v1-preview).
 # Usage
 Here is a snippet below for usage with Transformers:

   - In both standard and reasoning modes, Cogito v1-preview models outperform their size equivalent counterparts on common industry benchmarks.
 - Each model is trained in over 30 languages and supports a context length of 128k.
+# Evaluations
+We compare our models against the state of the art size equivalent models in direct mode as well as the reasoning mode. For the direct mode, we compare against Llama / Qwen instruct counterparts. For reasoning, we use Deepseek's R1 distilled counterparts / Qwen's QwQ model.
+<p align="left">
+  <img src="images/70b_benchmarks.png" alt="Logo" width="90%">
+</p>
+**Livebench Global Average:**
+<p align="left">
+  <img src="images/livebench_global_average.png" alt="Logo" width="80%">
+</p>
 For detailed evaluations, please refer to the [Blog Post](https://www.deepcogito.com/research/cogito-v1-preview).
 # Usage
 Here is a snippet below for usage with Transformers: