Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
license: mit
|
4 |
+
tags:
|
5 |
+
- chess
|
6 |
+
- game
|
7 |
+
- pytorch
|
8 |
+
- causal-lm
|
9 |
+
datasets:
|
10 |
+
- custom
|
11 |
+
widget:
|
12 |
+
- text: "1.e4"
|
13 |
+
example_title: "Chess Opening"
|
14 |
+
---
|
15 |
+
|
16 |
+
# tiny-gpt2-finetuned-ajem
|
17 |
+
|
18 |
+
Este es un modelo de lenguaje entrenado espec铆ficamente para jugar ajedrez usando notaci贸n algebraica est谩ndar.
|
19 |
+
|
20 |
+
## Uso
|
21 |
+
|
22 |
+
```python
|
23 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
24 |
+
|
25 |
+
tokenizer = AutoTokenizer.from_pretrained("tu-usuario/tiny-gpt2-finetuned-ajem")
|
26 |
+
model = AutoModelForCausalLM.from_pretrained("tu-usuario/tiny-gpt2-finetuned-ajem")
|
27 |
+
|
28 |
+
# Generar siguiente movimiento
|
29 |
+
input_text = "1.e4 e5 2.Nf3"
|
30 |
+
inputs = tokenizer.encode(input_text, return_tensors="pt")
|
31 |
+
outputs = model.generate(inputs, max_length=50, do_sample=True)
|
32 |
+
next_move = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
33 |
+
```
|
34 |
+
|
35 |
+
## Entrenamiento
|
36 |
+
|
37 |
+
Modelo entrenado en partidas de ajedrez usando PyTorch con arquitectura Transformer personalizada.
|