Instructions to use monsterapi/zephyr-7b-beta-CTranslate2-bfloat16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use monsterapi/zephyr-7b-beta-CTranslate2-bfloat16 with Transformers:

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

pipe = pipeline("text-generation", model="monsterapi/zephyr-7b-beta-CTranslate2-bfloat16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("monsterapi/zephyr-7b-beta-CTranslate2-bfloat16", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use monsterapi/zephyr-7b-beta-CTranslate2-bfloat16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "monsterapi/zephyr-7b-beta-CTranslate2-bfloat16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "monsterapi/zephyr-7b-beta-CTranslate2-bfloat16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/monsterapi/zephyr-7b-beta-CTranslate2-bfloat16

SGLang

How to use monsterapi/zephyr-7b-beta-CTranslate2-bfloat16 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 "monsterapi/zephyr-7b-beta-CTranslate2-bfloat16" \
    --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": "monsterapi/zephyr-7b-beta-CTranslate2-bfloat16",
		"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 "monsterapi/zephyr-7b-beta-CTranslate2-bfloat16" \
        --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": "monsterapi/zephyr-7b-beta-CTranslate2-bfloat16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use monsterapi/zephyr-7b-beta-CTranslate2-bfloat16 with Docker Model Runner:
```
docker model run hf.co/monsterapi/zephyr-7b-beta-CTranslate2-bfloat16
```

Currently Ctranslate2 does not directly support mistral and zephyr models for conversion

Here is a custom converted model made possible by some code changes to the ct2 repo for mistral. Mainly developed for internal development use you can use it too if your struggling with the same issue

Note: Model was created with BFloat16 quantization

license: apache-2.0

Downloads last month: 20