Instructions to use dev2bit/es2bash-mt5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dev2bit/es2bash-mt5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dev2bit/es2bash-mt5")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("dev2bit/es2bash-mt5") model = AutoModelForSeq2SeqLM.from_pretrained("dev2bit/es2bash-mt5") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dev2bit/es2bash-mt5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dev2bit/es2bash-mt5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dev2bit/es2bash-mt5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dev2bit/es2bash-mt5
- SGLang
How to use dev2bit/es2bash-mt5 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 "dev2bit/es2bash-mt5" \ --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": "dev2bit/es2bash-mt5", "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 "dev2bit/es2bash-mt5" \ --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": "dev2bit/es2bash-mt5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dev2bit/es2bash-mt5 with Docker Model Runner:
docker model run hf.co/dev2bit/es2bash-mt5
Commit ·
9df5ec3
1
Parent(s): 6c28bac
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,4 +8,45 @@ library_name: adapter-transformers
|
|
| 8 |
pipeline_tag: text2text-generation
|
| 9 |
tags:
|
| 10 |
- code
|
| 11 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
pipeline_tag: text2text-generation
|
| 9 |
tags:
|
| 10 |
- code
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# es2bash-mt5: Modelo de traducción de español a Bashcd
|
| 14 |
+
|
| 15 |
+
<p align="center">
|
| 16 |
+
<img width="460" height="300" src="https://dev2bit.com/wp-content/themes/lovecraft_child/assets/icons/dev2bit_monitor2.svg">
|
| 17 |
+
</p>
|
| 18 |
+
|
| 19 |
+
Desarrollado por dev2bit, `es2bash-mt5` es un modelo transformador de lenguaje que tiene la capacidad de predecir el comando Bash óptimo dada una solicitud en lenguaje natural en español. Este modelo representa un gran avance en la interacción humano-computadora, proporcionando una interfaz de lenguaje natural para los comandos del sistema operativo Unix.
|
| 20 |
+
|
| 21 |
+
## Sobre el modelo
|
| 22 |
+
|
| 23 |
+
`es2bash-mt5` es un modelo de ajuste fino basado en `mt5-small`. Ha sido entrenado en el conjunto de datos `dev2bit/es2bash`, especializado en la traducción de lenguaje natural en español a comandos Bash.
|
| 24 |
+
|
| 25 |
+
Este modelo está optimizado para procesar solicitudes relacionadas con los comandos:
|
| 26 |
+
* `cat`
|
| 27 |
+
* `ls`
|
| 28 |
+
* `cd`
|
| 29 |
+
|
| 30 |
+
## Uso
|
| 31 |
+
|
| 32 |
+
A continuación, se muestra un ejemplo de cómo usar `es2bash-mt5` con la biblioteca Hugging Face Transformers:
|
| 33 |
+
|
| 34 |
+
```python
|
| 35 |
+
from transformers import pipeline
|
| 36 |
+
|
| 37 |
+
translator = pipeline('translation', model='dev2bit/es2bash-mt5')
|
| 38 |
+
|
| 39 |
+
request = "listar los archivos en el directorio actual"
|
| 40 |
+
translated = translator(request, max_length=512)
|
| 41 |
+
print(translated[0]['translation_text'])
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
Esto imprimirá el comando Bash correspondiente a la solicitud dada en español.
|
| 45 |
+
|
| 46 |
+
## Contribuciones
|
| 47 |
+
|
| 48 |
+
Agradecemos sus contribuciones! Puede ayudar a mejorar es2bash-mt5 de varias formas, incluyendo:
|
| 49 |
+
|
| 50 |
+
* Probar el modelo y reportar cualquier problema o sugerencia en la sección de Issues.
|
| 51 |
+
* Mejorando la documentación.
|
| 52 |
+
* Proporcionando ejemplos de uso.
|