初始化项目,由ModelHub XC社区提供模型

Model: LorenzoDeMattei/GePpeTto
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-03 12:39:17 +08:00
commit b88816911f
14 changed files with 29965 additions and 0 deletions

10
.gitattributes vendored Normal file
View File

@@ -0,0 +1,10 @@
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tar.gz filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
model.safetensors filter=lfs diff=lfs merge=lfs -text

141
README.md Normal file
View File

@@ -0,0 +1,141 @@
---
language: it
---
# GePpeTto GPT2 Model 🇮🇹
Pretrained GPT2 117M model for Italian.
You can find further details in the paper:
Lorenzo De Mattei, Michele Cafagna, Felice DellOrletta, Malvina Nissim, Marco Guerini "GePpeTto Carves Italian into a Language Model", arXiv preprint. Pdf available at: https://arxiv.org/abs/2004.14253
## Pretraining Corpus
The pretraining set comprises two main sources. The first one is a dump of Italian Wikipedia (November 2019),
consisting of 2.8GB of text. The second one is the ItWac corpus (Baroni et al., 2009), which amounts to 11GB of web
texts. This collection provides a mix of standard and less standard Italian, on a rather wide chronological span,
with older texts than the Wikipedia dump (the latter stretches only to the late 2000s).
## Pretraining details
This model was trained using GPT2's Hugging Face implemenation on 4 NVIDIA Tesla T4 GPU for 620k steps.
Training parameters:
- GPT-2 small configuration
- vocabulary size: 30k
- Batch size: 32
- Block size: 100
- Adam Optimizer
- Initial learning rate: 5e-5
- Warm up steps: 10k
## Perplexity scores
| Domain | Perplexity |
|---|---|
| Wikipedia | 26.1052 |
| ItWac | 30.3965 |
| Legal | 37.2197 |
| News | 45.3859 |
| Social Media | 84.6408 |
For further details, qualitative analysis and human evaluation check out: https://arxiv.org/abs/2004.14253
## Load Pretrained Model
You can use this model by installing Huggingface library `transformers`. And you can use it directly by initializing it like this:
```python
from transformers import GPT2Tokenizer, GPT2Model
model = GPT2Model.from_pretrained('LorenzoDeMattei/GePpeTto')
tokenizer = GPT2Tokenizer.from_pretrained(
'LorenzoDeMattei/GePpeTto',
)
```
## Example using GPT2LMHeadModel
```python
from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline, GPT2Tokenizer
tokenizer = AutoTokenizer.from_pretrained("LorenzoDeMattei/GePpeTto")
model = AutoModelWithLMHead.from_pretrained("LorenzoDeMattei/GePpeTto")
text_generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
prompts = [
"Wikipedia Geppetto",
"Maestro Ciliegia regala il pezzo di legno al suo amico Geppetto, il quale lo prende per fabbricarsi un burattino maraviglioso"]
samples_outputs = text_generator(
prompts,
do_sample=True,
max_length=50,
top_k=50,
top_p=0.95,
num_return_sequences=3
)
for i, sample_outputs in enumerate(samples_outputs):
print(100 * '-')
print("Prompt:", prompts[i])
for sample_output in sample_outputs:
print("Sample:", sample_output['generated_text'])
print()
```
Output is,
```
----------------------------------------------------------------------------------------------------
Prompt: Wikipedia Geppetto
Sample: Wikipedia Geppetto rosso (film 1920)
Geppetto rosso ("The Smokes in the Black") è un film muto del 1920 diretto da Henry H. Leonard.
Il film fu prodotto dalla Selig Poly
Sample: Wikipedia Geppetto
Geppetto ("Geppetto" in piemontese) è un comune italiano di 978 abitanti della provincia di Cuneo in Piemonte.
L'abitato, che si trova nel versante valtellinese, si sviluppa nella
Sample: Wikipedia Geppetto di Natale (romanzo)
Geppetto di Natale è un romanzo di Mario Caiano, pubblicato nel 2012.
----------------------------------------------------------------------------------------------------
Prompt: Maestro Ciliegia regala il pezzo di legno al suo amico Geppetto, il quale lo prende per fabbricarsi un burattino maraviglioso
Sample: Maestro Ciliegia regala il pezzo di legno al suo amico Geppetto, il quale lo prende per fabbricarsi un burattino maraviglioso. Il burattino riesce a scappare. Dopo aver trovato un prezioso sacchetto si reca
Sample: Maestro Ciliegia regala il pezzo di legno al suo amico Geppetto, il quale lo prende per fabbricarsi un burattino maraviglioso, e l'unico che lo possiede, ma, di fronte a tutte queste prove
Sample: Maestro Ciliegia regala il pezzo di legno al suo amico Geppetto, il quale lo prende per fabbricarsi un burattino maraviglioso: - A voi gli occhi, le guance! A voi il mio pezzo!
```
## Citation
Please use the following bibtex entry:
```
@misc{mattei2020geppetto,
title={GePpeTto Carves Italian into a Language Model},
author={Lorenzo De Mattei and Michele Cafagna and Felice Dell'Orletta and Malvina Nissim and Marco Guerini},
year={2020},
eprint={2004.14253},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## References
Marco Baroni, Silvia Bernardini, Adriano Ferraresi,
and Eros Zanchetta. 2009. The WaCky wide web: a
collection of very large linguistically processed webcrawled corpora. Language resources and evaluation, 43(3):209226.

51
config.json Normal file
View File

@@ -0,0 +1,51 @@
{
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 0,
"do_sample": false,
"embd_pdrop": 0.1,
"eos_token_ids": 0,
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"is_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_epsilon": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_layer": 12,
"n_positions": 1024,
"num_beams": 1,
"num_labels": 2,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_past": true,
"pad_token_id": 0,
"pruned_heads": {},
"repetition_penalty": 1.0,
"resid_pdrop": 0.1,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"use_bfloat16": false,
"vocab_size": 30000
}

1
eval_results.txt Normal file
View File

@@ -0,0 +1 @@
perplexity = tensor(84.6408)

3
flax_model.msgpack Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca9de9868952bbf26c5ed657e3eefb15de6cdbcc8613d0ef932534ed1d34a667
size 435534616

29744
merges.txt Normal file

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09ba4d3ef3c88413fdaa27dc36dc160329b8074c2c8da7d653d7c9b0888cb0fe
size 485877646

3
optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be324024bb4655c35201f86034a4df0d0eae8fc951b0ead73d227a6a2044ecd4
size 871104258

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:df874cf7f61b14f53f27c332086eac7f978403cd923a10a477fc8e46e3eff8a7
size 485894375

BIN
scheduler.pt Normal file

Binary file not shown.

1
special_tokens_map.json Normal file
View File

@@ -0,0 +1 @@
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

1
tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dab0bb3640a6fb8619418a8d436a27e1668e25a612dbe519ff4482893016953f
size 1370

1
vocab.json Normal file

File diff suppressed because one or more lines are too long