Instructions to use galatolo/cerbero-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use galatolo/cerbero-7b with Transformers:

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

pipe = pipeline("text-generation", model="galatolo/cerbero-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("galatolo/cerbero-7b")
model = AutoModelForCausalLM.from_pretrained("galatolo/cerbero-7b")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use galatolo/cerbero-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/galatolo/cerbero-7b

SGLang

How to use galatolo/cerbero-7b 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 "galatolo/cerbero-7b" \
    --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": "galatolo/cerbero-7b",
		"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 "galatolo/cerbero-7b" \
        --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": "galatolo/cerbero-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use galatolo/cerbero-7b with Docker Model Runner:
```
docker model run hf.co/galatolo/cerbero-7b
```

Unable to load model in GPU

by Federic - opened Dec 5, 2023

Discussion

Federic

Dec 5, 2023

Hi I'm trying to play with this model, but i cannot load it in gpu (T4 16GB provided by Colab), even if I specify device_map="cuda:0" it still loads in RAM. Any advice? I have another question why the model weights so much ~ 30GB despite having 7B parameters?

import transformers
quantization_config = transformers.BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type='nf4',
bnb_4bit_use_double_quant=True,
#bnb_4bit_compute_dtype=bfloat16
)

llm = AutoModelForCausalLM.from_pretrained(
"galatolo/cerbero-7b",
quantization_config = quantization_config,
device_map="cuda:0"
)

galatolo

Owner Dec 5, 2023

Hi, it weighs that much because the weights are in the float32 format (rather than the more common float16).
I attempted to load the model using Google Colab, and it appears to crash due to insufficient RAM.
I will upload a float16 variant, maybe it will solve this issue

galatolo

Owner Dec 5, 2023

•

edited Dec 5, 2023

I uploaded the float16 variant, and you can load it using the following code:

model = AutoModelForCausalLM.from_pretrained("galatolo/cerbero-7b", revision="float16")

However, it appears that Colab does not have enough RAM to handle this. I believe the best option is to use the llama.cpp version, which I have already quantized to 4 bits.

galatolo changed discussion status to closed Dec 7, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment