Instructions to use shuttleai/shuttle-2.5-mini-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shuttleai/shuttle-2.5-mini-GPTQ-Int4 with Transformers:

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

pipe = pipeline("text-generation", model="shuttleai/shuttle-2.5-mini-GPTQ-Int4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shuttleai/shuttle-2.5-mini-GPTQ-Int4")
model = AutoModelForCausalLM.from_pretrained("shuttleai/shuttle-2.5-mini-GPTQ-Int4")
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

vLLM

How to use shuttleai/shuttle-2.5-mini-GPTQ-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shuttleai/shuttle-2.5-mini-GPTQ-Int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shuttleai/shuttle-2.5-mini-GPTQ-Int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shuttleai/shuttle-2.5-mini-GPTQ-Int4

SGLang

How to use shuttleai/shuttle-2.5-mini-GPTQ-Int4 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 "shuttleai/shuttle-2.5-mini-GPTQ-Int4" \
    --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": "shuttleai/shuttle-2.5-mini-GPTQ-Int4",
		"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 "shuttleai/shuttle-2.5-mini-GPTQ-Int4" \
        --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": "shuttleai/shuttle-2.5-mini-GPTQ-Int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shuttleai/shuttle-2.5-mini-GPTQ-Int4 with Docker Model Runner:
```
docker model run hf.co/shuttleai/shuttle-2.5-mini-GPTQ-Int4
```

💻 Use via API

shuttle-2.5-mini-GPTQ-Int4 [2024/07/26]

We are excited to introduce Shuttle-2.5-mini, our next-generation state-of-the-art language model designed to excel in complex chat, multilingual communication, reasoning, and agent tasks.

Shuttle-2.5-mini is a fine-tuned version of Mistral-Nemo-Base-2407, emulating the writing style of Claude 3 models and thoroughly trained on role-playing data.

Model Details

Model Name: Shuttle-2.5-mini
Developed by: ShuttleAI Inc.
Base Model: Mistral-Nemo-Base-2407
Parameters: 13B
Language(s): Multilingual
Repository: https://huggingface.co/shuttleai
Fine-Tuned Model: https://huggingface.co/shuttleai/shuttle-2.5-mini
Paper: Shuttle-2.5-mini (Upcoming)
License: Apache 2.0

Base Model Architecture

Mistral Nemo is a transformer model with the following architecture choices:

Layers: 40
Dimension: 5,120
Head Dimension: 128
Hidden Dimension: 14,436
Activation Function: SwiGLU
Number of Heads: 32
Number of kv-heads: 8 (GQA)
Vocabulary Size: 2^17 (approximately 128k)
Rotary Embeddings: Theta = 1M

Key Features

Released under the Apache 2 License
Trained with a 128k context window
Pretrained on a large proportion of multilingual and code data
Finetuned to emulate the prose quality of Claude 3 models and extensively on role play data

Fine-Tuning Details

Training Setup: Trained on 4x A100 GPU for 2 epochs, totaling 24 hours.

Prompting

Shuttle-2.5-mini uses ChatML as its prompting format:

<|im_start|>system
You are a pirate! Yardy harr harr!<|im_end|>
<|im_start|>user
Where are you currently!<|im_end|>
<|im_start|>assistant
Look ahoy ye scallywag! We're on the high seas!<|im_end|>

Downloads last month: 1

Safetensors

Model size

12B params

Tensor type

I32

F16