Instructions to use mlabonne/llama-2-13b-miniguanaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlabonne/llama-2-13b-miniguanaco with Transformers:

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

pipe = pipeline("text-generation", model="mlabonne/llama-2-13b-miniguanaco")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlabonne/llama-2-13b-miniguanaco")
model = AutoModelForCausalLM.from_pretrained("mlabonne/llama-2-13b-miniguanaco", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mlabonne/llama-2-13b-miniguanaco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlabonne/llama-2-13b-miniguanaco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlabonne/llama-2-13b-miniguanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlabonne/llama-2-13b-miniguanaco

SGLang

How to use mlabonne/llama-2-13b-miniguanaco 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 "mlabonne/llama-2-13b-miniguanaco" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlabonne/llama-2-13b-miniguanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "mlabonne/llama-2-13b-miniguanaco" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlabonne/llama-2-13b-miniguanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mlabonne/llama-2-13b-miniguanaco with Docker Model Runner:
```
docker model run hf.co/mlabonne/llama-2-13b-miniguanaco
```

🦙🧠 Miniguanaco-13b

📝 Article | 💻 Colab | 📄 Script

This is a Llama-2-13b-chat-hf model fine-tuned using QLoRA (4-bit precision) on the mlabonne/guanaco-llama2-1k dataset, which is a subset of the timdettmers/openassistant-guanaco.

🔧 Training

It was trained on an RTX 3090. It is mainly designed for educational purposes, not for inference. Parameters:

max_seq_length = 2048
use_nested_quant = True
bnb_4bit_compute_dtype=bfloat16
lora_r=8
lora_alpha=16
lora_dropout=0.05
per_device_train_batch_size=2

💻 Usage

# pip install transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/llama-2-13b-miniguanaco"
prompt = "What is a large language model?"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

sequences = pipeline(
    f'<s>[INST] {prompt} [/INST]',
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=200,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

Downloads last month: 8

Dataset used to train mlabonne/llama-2-13b-miniguanaco

Collection including mlabonne/llama-2-13b-miniguanaco

🦙 Llama 2 Guanaco

Collection

Set of models fine-tuned using QLoRA on Google Colab with the Guanaco dataset. • 4 items • Updated Aug 16, 2024