Instructions to use Undi95/Mistral-11B-CC-Air with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/Mistral-11B-CC-Air with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/Mistral-11B-CC-Air")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/Mistral-11B-CC-Air")
model = AutoModelForCausalLM.from_pretrained("Undi95/Mistral-11B-CC-Air")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/Mistral-11B-CC-Air with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/Mistral-11B-CC-Air"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/Mistral-11B-CC-Air",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/Mistral-11B-CC-Air

SGLang

How to use Undi95/Mistral-11B-CC-Air 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 "Undi95/Mistral-11B-CC-Air" \
    --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": "Undi95/Mistral-11B-CC-Air",
		"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 "Undi95/Mistral-11B-CC-Air" \
        --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": "Undi95/Mistral-11B-CC-Air",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/Mistral-11B-CC-Air with Docker Model Runner:
```
docker model run hf.co/Undi95/Mistral-11B-CC-Air
```

CollectiveCognition-v1.1-Mistral-7B and airoboros-mistral2.2-7b glued together.

Description

This repo contains fp16 files of Mistral-11B-CC-Air.

Model used

Prompt template: Alpaca or default

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

USER: <prompt>
ASSISTANT:

The secret sauce

slices:
  - sources:
    - model: teknium/CollectiveCognition-v1.1-Mistral-7B
      layer_range: [0, 24]
  - sources:
    - model: teknium/airoboros-mistral2.2-7b
      layer_range: [8, 32]
merge_method: passthrough
dtype: float16

Special thanks to Sushi.

If you want to support me, you can here.

Downloads last month: 9

Safetensors

Model size

11B params

Tensor type

F16