Instructions to use reddest-panda/AutoMAD-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reddest-panda/AutoMAD-small with Transformers:

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

pipe = pipeline("text-generation", model="reddest-panda/AutoMAD-small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reddest-panda/AutoMAD-small")
model = AutoModelForCausalLM.from_pretrained("reddest-panda/AutoMAD-small", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use reddest-panda/AutoMAD-small with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reddest-panda/AutoMAD-small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/reddest-panda/AutoMAD-small

SGLang

How to use reddest-panda/AutoMAD-small 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 "reddest-panda/AutoMAD-small" \
    --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": "reddest-panda/AutoMAD-small",
		"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 "reddest-panda/AutoMAD-small" \
        --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": "reddest-panda/AutoMAD-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use reddest-panda/AutoMAD-small with Docker Model Runner:
```
docker model run hf.co/reddest-panda/AutoMAD-small
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

Usage


from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "reddest-panda/AutoMAD-small"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

# Prompt content: "hi"
messages = [
    {"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

# Model response: "Hello! How can I assist you today?"
print(response)

Downloads last month: 12

Safetensors

Model size

0.5B params

Tensor type

BF16

Model tree for reddest-panda/AutoMAD-small

Base model

Qwen/Qwen2-0.5B

Finetuned

Qwen/Qwen2-0.5B-Instruct

Finetuned

(603)

this model

Quantizations

1 model

reddest-panda
/

AutoMAD-small

Model Trained Using AutoTrain

Usage

Model tree for reddest-panda/AutoMAD-small

Dataset used to train reddest-panda/AutoMAD-small