Instructions to use marianbasti/Llama-2-13b-alpaca-spanish-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marianbasti/Llama-2-13b-alpaca-spanish-LoRA with Transformers:

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

pipe = pipeline("text-generation", model="marianbasti/Llama-2-13b-alpaca-spanish-LoRA")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("marianbasti/Llama-2-13b-alpaca-spanish-LoRA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use marianbasti/Llama-2-13b-alpaca-spanish-LoRA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/marianbasti/Llama-2-13b-alpaca-spanish-LoRA

SGLang

How to use marianbasti/Llama-2-13b-alpaca-spanish-LoRA 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 "marianbasti/Llama-2-13b-alpaca-spanish-LoRA" \
    --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": "marianbasti/Llama-2-13b-alpaca-spanish-LoRA",
		"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 "marianbasti/Llama-2-13b-alpaca-spanish-LoRA" \
        --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": "marianbasti/Llama-2-13b-alpaca-spanish-LoRA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use marianbasti/Llama-2-13b-alpaca-spanish-LoRA with Docker Model Runner:
```
docker model run hf.co/marianbasti/Llama-2-13b-alpaca-spanish-LoRA
```

Llama 2-13b-alpaca-spanish LoRA

This is a LoRA for Llama 2 13B trained on a translated alpaca dataset on an attempt to improve spanish performance of the Llama-2 foundation model with a conversational focus.

Base model used was The Bloke's Llama-2-13B-fp16 trained in 4bit precision with an added padding token.

Important INFO

The original Llama 2 model does not have a padding token, this came to be restrictive when training. To address this, I added a padding token to the tokenizer associated with the model.

from transformers import LlamaTokenizer, LlamaForCausalLM

model_name = 'TheBloke/Llama-2-13B-fp16'

model = LlamaForCausalLM.from_pretrained(model_name).half()
tokenizer = LlamaTokenizer.from_pretrained(model_name)

# Add padding token
tokenizer.add_tokens(['<PAD>'])
tokenizer.pad_token = '<PAD>'

# Resizing the model
model.resize_token_embeddings(len(tokenizer))

padded_model_name = 'Llama-2-13B-fp16-padded'

# Save
tokenizer.save_pretrained(padded_model_name)
model.save_pretrained(padded_model_name)

Training parameteres
LoRA scale	2
Epochs	0.75
Learning Rate	2e-5
Warmup Steps	100
Loss	1.07

Downloads last month: -; Downloads are not tracked for this model. How to track

marianbasti
/

Llama-2-13b-alpaca-spanish-LoRA

Llama 2-13b-alpaca-spanish LoRA

Important INFO

Dataset used to train marianbasti/Llama-2-13b-alpaca-spanish-LoRA