Instructions to use Fifthoply/AyudaAlan-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fifthoply/AyudaAlan-0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Fifthoply/AyudaAlan-0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fifthoply/AyudaAlan-0.1")
model = AutoModelForCausalLM.from_pretrained("Fifthoply/AyudaAlan-0.1")
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 Fifthoply/AyudaAlan-0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fifthoply/AyudaAlan-0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fifthoply/AyudaAlan-0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fifthoply/AyudaAlan-0.1

SGLang

How to use Fifthoply/AyudaAlan-0.1 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 "Fifthoply/AyudaAlan-0.1" \
    --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": "Fifthoply/AyudaAlan-0.1",
		"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 "Fifthoply/AyudaAlan-0.1" \
        --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": "Fifthoply/AyudaAlan-0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fifthoply/AyudaAlan-0.1 with Docker Model Runner:
```
docker model run hf.co/Fifthoply/AyudaAlan-0.1
```

AyudaAlan-0.1 / README.md

Fifthoply

Update README.md

d4e7c85 verified 16 days ago

preview code

raw

history blame contribute delete

1.86 kB

	---
	license: mit
	language:
	- es
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- tiny-model
	- sarcasm
	---

	# Ayuda Alan 0.1


	### Ejemplo de comportamiento
	* Usuario: ¿Cómo escalo una montaña?
	* Modelo: Escalándola.

	---

	# ¿Cómo usar el modelo?

	La mejor forma es ir al espacio de Hugging Face creado para este modelo:

	```
	https://huggingface.co/spaces/Fifthoply/AyudaAlan-0.1
	```

	Para utilizar este modelo en tu computadora, asegúrate de tener instalada la librería `transformers`, no necesitas GPU:

	```bash
	pip install transformers torch
	```

	Luego, puedes usar el siguiente script de Python:

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	# 1. Cargar el modelo y el tokenizador
	model_id = "tu-usuario/tu-modelo" # Reemplaza con tu ID de Hugging Face
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	torch_dtype=torch.float16,
	device_map="auto"
	)

	# 2. Preparar el mensaje (Formato ChatML)
	pregunta = "¿Cómo se escala una montaña?"
	prompt = f"<\|im_start\|>system\nEres un asistente breve.<\|im_end\|>\n<\|im_start\|>user\n{pregunta}<\|im_end\|>\n<\|im_start\|>assistant\n"

	# 3. Tokenizar y generar respuesta
	inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

	outputs = model.generate(
	**inputs,
	max_new_tokens=20,
	pad_token_id=tokenizer.pad_token_id,
	eos_token_id=tokenizer.eos_token_id
	)

	# 4. Ver el resultado
	respuesta = tokenizer.decode(outputs[0], skip_special_tokens=True)
	print(respuesta.split("assistant")[-1].strip())
	```

	---
	Nota: Este modelo fue entrenado con un dataset específico de frases con redudancia extrema—el motivo principal de la
	broma AyudaAlaN—su conocimiento general sigue presente, pero su estilo de respuesta priorizará siempre la brevedad extrema.