Instructions to use jeduardogruiz/Mixtral_ether with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Adapters
How to use jeduardogruiz/Mixtral_ether with Adapters:
from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("fill-in-model-name") model.load_adapter("jeduardogruiz/Mixtral_ether", set_active=True) - Notebooks
- Google Colab
- Kaggle
Create readme.md
Browse files
readme.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 3 |
+
|
| 4 |
+
model_id = "jeduardogruiz/Mixtral_ether"
|
| 5 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 6 |
+
model = AutoModelForCausalLM.from_pretrained(model_id)
|
| 7 |
+
|
| 8 |
+
# Define el mensaje que deseas enviar al bot
|
| 9 |
+
mensaje = "¿Cuál es tu condimento favorito?"
|
| 10 |
+
|
| 11 |
+
# Tokeniza el mensaje
|
| 12 |
+
inputs = tokenizer(mensaje, return_tensors="pt")
|
| 13 |
+
|
| 14 |
+
# Genera la respuesta del bot
|
| 15 |
+
outputs = model.generate(inputs, max_new_tokens=20)
|
| 16 |
+
|
| 17 |
+
# Decodifica la respuesta
|
| 18 |
+
respuesta = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 19 |
+
|
| 20 |
+
print(respuesta)
|