Hjgugugjhuhjggg
commited on
Subida del modelo ajustado con 1 capas, hidden_size=2 y vocab_size=50259 y README.md
Browse files- README.md +55 -0
- added_tokens.json +4 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +22 -0
- tokenizer.json +0 -0
- tokenizer_config.json +41 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
language: en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- text-generation
|
7 |
+
- gpt2
|
8 |
+
library_name: transformers
|
9 |
+
pipeline_tag: text-generation
|
10 |
+
---
|
11 |
+
# Modelo Ajustado para Generación de Texto
|
12 |
+
|
13 |
+
Este modelo ha sido ajustado a partir de `gpt2` con la siguiente configuración:
|
14 |
+
|
15 |
+
- Número de capas ocultas: 1
|
16 |
+
- Tamaño de la capa oculta: 2
|
17 |
+
- Tamaño del vocabulario: 50259
|
18 |
+
|
19 |
+
**Importante:** Este modelo utiliza la arquitectura base de `gpt2` y **ha eliminado capas internas**. El modelo original tenía 12 capas, **y ahora tiene solo 1 capa oculta**. Además, se han añadido nuevos tokens al vocabulario y sus embeddings han sido inicializados.
|
20 |
+
|
21 |
+
Se puede utilizar para tareas de generación de texto.
|
22 |
+
|
23 |
+
## Uso
|
24 |
+
|
25 |
+
Para usar este modelo, primero debes tener instalada la librería `transformers`. Puedes instalarla usando pip:
|
26 |
+
|
27 |
+
|
28 |
+
pip install transformers
|
29 |
+
|
30 |
+
|
31 |
+
Una vez instalada, puedes cargar y usar el modelo de la siguiente manera:
|
32 |
+
|
33 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
34 |
+
|
35 |
+
repo_name = "lilmeaty/text-gen-example-one-layer"
|
36 |
+
model = AutoModelForCausalLM.from_pretrained(repo_name)
|
37 |
+
tokenizer = AutoTokenizer.from_pretrained(repo_name)
|
38 |
+
|
39 |
+
prompt = "Escribe una breve historia sobre un robot que aprende a amar."
|
40 |
+
input_ids = tokenizer.encode(prompt, return_tensors="pt")
|
41 |
+
|
42 |
+
output = model.generate(
|
43 |
+
input_ids,
|
44 |
+
max_length=100,
|
45 |
+
num_return_sequences=1,
|
46 |
+
no_repeat_ngram_size=2,
|
47 |
+
top_k=50,
|
48 |
+
top_p=0.95,
|
49 |
+
temperature=0.7,
|
50 |
+
do_sample=True
|
51 |
+
)
|
52 |
+
|
53 |
+
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
54 |
+
print(generated_text)
|
55 |
+
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[SPECIAL1]": 50257,
|
3 |
+
"[SPECIAL2]": 50258
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 2,
|
17 |
+
"n_head": 1,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 1,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"transformers_version": "4.47.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50259
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.47.1"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ded1a55fb9c92fbed8902f0599ef164a0bf632949cedde9a3c65b83d476f7cf5
|
3 |
+
size 185900592
|
special_tokens_map.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "[SPECIAL1]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "[SPECIAL2]",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<|endoftext|>",
|
19 |
+
"eos_token": "<|endoftext|>",
|
20 |
+
"pad_token": "<|endoftext|>",
|
21 |
+
"unk_token": "<|endoftext|>"
|
22 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": "[SPECIAL1]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50258": {
|
21 |
+
"content": "[SPECIAL2]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"[SPECIAL1]",
|
31 |
+
"[SPECIAL2]"
|
32 |
+
],
|
33 |
+
"bos_token": "<|endoftext|>",
|
34 |
+
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "<|endoftext|>",
|
36 |
+
"extra_special_tokens": {},
|
37 |
+
"model_max_length": 1024,
|
38 |
+
"pad_token": "<|endoftext|>",
|
39 |
+
"tokenizer_class": "GPT2Tokenizer",
|
40 |
+
"unk_token": "<|endoftext|>"
|
41 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|