Instructions to use dyvanoff/Referencias-de-Vinos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dyvanoff/Referencias-de-Vinos with Transformers:

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

pipe = pipeline("text-generation", model="dyvanoff/Referencias-de-Vinos")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dyvanoff/Referencias-de-Vinos")
model = AutoModelForCausalLM.from_pretrained("dyvanoff/Referencias-de-Vinos", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dyvanoff/Referencias-de-Vinos with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dyvanoff/Referencias-de-Vinos

SGLang

How to use dyvanoff/Referencias-de-Vinos 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 "dyvanoff/Referencias-de-Vinos" \
    --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": "dyvanoff/Referencias-de-Vinos",
		"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 "dyvanoff/Referencias-de-Vinos" \
        --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": "dyvanoff/Referencias-de-Vinos",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dyvanoff/Referencias-de-Vinos with Docker Model Runner:
```
docker model run hf.co/dyvanoff/Referencias-de-Vinos
```

Referencias-de-Vinos

This model is a fine-tuned version of DeepESP/gpt2-spanish on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.9310

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.9201	1.0	3000	2.0543
1.7335	2.0	6000	1.9645
1.6038	3.0	9000	1.9353
1.9135	4.0	12000	1.9310

Framework versions

Transformers 4.33.1
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3

Downloads last month: 10

Model tree for dyvanoff/Referencias-de-Vinos

Base model

DeepESP/gpt2-spanish

Finetuned

(72)

this model