Instructions to use Kquant03/Cognito-2x7B-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kquant03/Cognito-2x7B-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="Kquant03/Cognito-2x7B-bf16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kquant03/Cognito-2x7B-bf16")
model = AutoModelForCausalLM.from_pretrained("Kquant03/Cognito-2x7B-bf16")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kquant03/Cognito-2x7B-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kquant03/Cognito-2x7B-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/Cognito-2x7B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kquant03/Cognito-2x7B-bf16

SGLang

How to use Kquant03/Cognito-2x7B-bf16 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 "Kquant03/Cognito-2x7B-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/Cognito-2x7B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Kquant03/Cognito-2x7B-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/Cognito-2x7B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kquant03/Cognito-2x7B-bf16 with Docker Model Runner:
```
docker model run hf.co/Kquant03/Cognito-2x7B-bf16
```

Update README.md

by NeuralNovel - opened Feb 4, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-2

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -9,10 +9,10 @@ tags:
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/YIxTRkaxXfPL9NHM6ZL76.jpeg)
-Knowledge is **power**.
 # Kquant03/Cognito-2x7B-bf16
 [Join our Discord!](https://discord.gg/aEGuFph9)
 A frankenMoE using zero positive prompting for the config. (designed by [NeuralNovel](https://huggingface.co/NeuralNovel))

 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/YIxTRkaxXfPL9NHM6ZL76.jpeg)
 # Kquant03/Cognito-2x7B-bf16
+Knowledge is **power**.
 [Join our Discord!](https://discord.gg/aEGuFph9)
 A frankenMoE using zero positive prompting for the config. (designed by [NeuralNovel](https://huggingface.co/NeuralNovel))