Hugging Face's logo

RichardErkhov
/
GroNLP_-_gpt2-small-italian-embeddings-gguf

GGUF
Model card Files Community
RichardErkhov commited on
Commit
5f12466
•
1 Parent(s): 535572e

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +107 -0
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ gpt2-small-italian-embeddings - GGUF
11
+ - Model creator: https://huggingface.co/GroNLP/
12
+ - Original model: https://huggingface.co/GroNLP/gpt2-small-italian-embeddings/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [gpt2-small-italian-embeddings.Q2_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q2_K.gguf) | Q2_K | 0.06GB |
18
+ | [gpt2-small-italian-embeddings.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.IQ3_XS.gguf) | IQ3_XS | 0.06GB |
19
+ | [gpt2-small-italian-embeddings.IQ3_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.IQ3_S.gguf) | IQ3_S | 0.06GB |
20
+ | [gpt2-small-italian-embeddings.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q3_K_S.gguf) | Q3_K_S | 0.06GB |
21
+ | [gpt2-small-italian-embeddings.IQ3_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.IQ3_M.gguf) | IQ3_M | 0.07GB |
22
+ | [gpt2-small-italian-embeddings.Q3_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q3_K.gguf) | Q3_K | 0.07GB |
23
+ | [gpt2-small-italian-embeddings.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q3_K_M.gguf) | Q3_K_M | 0.07GB |
24
+ | [gpt2-small-italian-embeddings.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q3_K_L.gguf) | Q3_K_L | 0.07GB |
25
+ | [gpt2-small-italian-embeddings.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.IQ4_XS.gguf) | IQ4_XS | 0.07GB |
26
+ | [gpt2-small-italian-embeddings.Q4_0.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q4_0.gguf) | Q4_0 | 0.08GB |
27
+ | [gpt2-small-italian-embeddings.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.IQ4_NL.gguf) | IQ4_NL | 0.08GB |
28
+ | [gpt2-small-italian-embeddings.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q4_K_S.gguf) | Q4_K_S | 0.08GB |
29
+ | [gpt2-small-italian-embeddings.Q4_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q4_K.gguf) | Q4_K | 0.08GB |
30
+ | [gpt2-small-italian-embeddings.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q4_K_M.gguf) | Q4_K_M | 0.08GB |
31
+ | [gpt2-small-italian-embeddings.Q4_1.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q4_1.gguf) | Q4_1 | 0.08GB |
32
+ | [gpt2-small-italian-embeddings.Q5_0.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q5_0.gguf) | Q5_0 | 0.09GB |
33
+ | [gpt2-small-italian-embeddings.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q5_K_S.gguf) | Q5_K_S | 0.09GB |
34
+ | [gpt2-small-italian-embeddings.Q5_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q5_K.gguf) | Q5_K | 0.09GB |
35
+ | [gpt2-small-italian-embeddings.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q5_K_M.gguf) | Q5_K_M | 0.09GB |
36
+ | [gpt2-small-italian-embeddings.Q5_1.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q5_1.gguf) | Q5_1 | 0.1GB |
37
+ | [gpt2-small-italian-embeddings.Q6_K.gguf](https://huggingface.co/RichardErkhov/GroNLP_-_gpt2-small-italian-embeddings-gguf/blob/main/gpt2-small-italian-embeddings.Q6_K.gguf) | Q6_K | 0.1GB |
38
+
39
+
40
+
41
+
42
+ Original model description:
43
+ ---
44
+ language: it
45
+ tags:
46
+ - adaption
47
+ - recycled
48
+ - gpt2-small
49
+ pipeline_tag: text-generation
50
+ ---
51
+
52
+ # GPT-2 recycled for Italian (small, adapted lexical embeddings)
53
+ [Wietse de Vries](https://www.semanticscholar.org/author/Wietse-de-Vries/144611157) •
54
+ [Malvina Nissim](https://www.semanticscholar.org/author/M.-Nissim/2742475)
55
+
56
+ ## Model description
57
+
58
+ This model is based on the small OpenAI GPT-2 ([`gpt2`](https://huggingface.co/gpt2)) model.
59
+
60
+ The Transformer layer weights in this model are identical to the original English, model but the lexical layer has been retrained for an Italian vocabulary.
61
+
62
+ For details, check out our paper on [arXiv](https://arxiv.org/abs/2012.05628) and the code on [Github](https://github.com/wietsedv/gpt2-recycle).
63
+
64
+
65
+ ## Related models
66
+
67
+ ### Dutch
68
+ - [`gpt2-small-dutch-embeddings`](https://huggingface.co/GroNLP/gpt2-small-dutch-embeddings): Small model size with only retrained lexical embeddings.
69
+ - [`gpt2-small-dutch`](https://huggingface.co/GroNLP/gpt2-small-dutch): Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (**Recommended**)
70
+ - [`gpt2-medium-dutch-embeddings`](https://huggingface.co/GroNLP/gpt2-medium-dutch-embeddings): Medium model size with only retrained lexical embeddings.
71
+
72
+ ### Italian
73
+ - [`gpt2-small-italian-embeddings`](https://huggingface.co/GroNLP/gpt2-small-italian-embeddings): Small model size with only retrained lexical embeddings.
74
+ - [`gpt2-small-italian`](https://huggingface.co/GroNLP/gpt2-small-italian): Small model size with retrained lexical embeddings and additional fine-tuning of the full model. (**Recommended**)
75
+ - [`gpt2-medium-italian-embeddings`](https://huggingface.co/GroNLP/gpt2-medium-italian-embeddings): Medium model size with only retrained lexical embeddings.
76
+
77
+
78
+ ## How to use
79
+
80
+ ```python
81
+ from transformers import pipeline
82
+
83
+ pipe = pipeline("text-generation", model="GroNLP/gpt2-small-italian-embeddings")
84
+ ```
85
+
86
+ ```python
87
+ from transformers import AutoTokenizer, AutoModel, TFAutoModel
88
+
89
+ tokenizer = AutoTokenizer.from_pretrained("GroNLP/gpt2-small-italian-embeddings")
90
+ model = AutoModel.from_pretrained("GroNLP/gpt2-small-italian-embeddings") # PyTorch
91
+ model = TFAutoModel.from_pretrained("GroNLP/gpt2-small-italian-embeddings") # Tensorflow
92
+ ```
93
+
94
+ ## BibTeX entry
95
+
96
+ ```bibtex
97
+ @misc{devries2020good,
98
+ title={As good as new. How to successfully recycle English GPT-2 to make models for other languages},
99
+ author={Wietse de Vries and Malvina Nissim},
100
+ year={2020},
101
+ eprint={2012.05628},
102
+ archivePrefix={arXiv},
103
+ primaryClass={cs.CL}
104
+ }
105
+ ```
106
+
107
+