Instructions to use arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer")
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer

SGLang

How to use arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer 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 "arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer" \
    --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": "arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer",
		"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 "arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer" \
        --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": "arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer
```

Why is the size of pruned model bigger than the original ones after 24 layers been sliced?

by iheardyoulooking - opened Apr 11, 2024

Discussion

iheardyoulooking

Apr 11, 2024

Usually after structured pruning the model size should be smaller. but
the original one: 15GB
sliced one: 20GB+

thomasgauthier

Apr 11, 2024

•

edited Apr 11, 2024

@iheardyoulooking it's because the model has been uploaded in 32 bit float format where the original Mistral is bfloat16. That makes each param in the sliced version twice as big on disk

You can still load the model in 16 bit by passing a torch_dtypeargument

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer')
model = AutoModelForCausalLM.from_pretrained(
    'arcee-ai/Mistral-7B-Instruct-v0.2-sliced-24-layer',
    torch_dtype=torch.bfloat16
)