Upload folder using huggingface_hub

Readme.md

@@ -0,0 +1,101 @@
+---
+license: mit
+datasets:
+- ccnet-fr
+language:
+- fr
+tags:
+- pagnol
+---
+
+# PAGnol: An Extra-Large French Generative Model
+
+Paper: [ARXIV](https://arxiv.org/abs/2110.08554), [ACL ANTHOLOGY](https://aclanthology.org/2022.lrec-1.455/)
+
+Code: [GITHUB](https://github.com/lightonai/lairgpt)
+
+PAGnol is a collection of large French language models, geared towards free-form text generation. With 1.5 billion parameters. PAGnol is based on the [GPT](https://arxiv.org/abs/2005.14165) architecture. PAGnol is the first language model trained by [LightOn](https://lighton.ai/), in cooperation with the [ALMAnaCH team of Inria](http://almanach.inria.fr/index-en.html).
+
+These model were trained in early 2021 following the then [scaling laws](https://arxiv.org/abs/2001.08361) and using the exact same training data as the [CamemBERT](https://camembert-model.fr/) model trained on [CCNet](https://github.com/facebookresearch/cc_net). We make it available for reproducibility and transparency purposes.
+They do not constitute the current state of the art nor are they aiming at it.
+
+PAGnol was built by [Julien Launay](https://lolo.science/), E.L. Tommasone, [Baptiste Pannier](https://www.linkedin.com/in/baptiste-pannier-b30758154/), [François Boniface](https://www.linkedin.com/in/fran%c3%a7ois-boniface-26313610b/), [Amélie Chatelain](https://www.instagram.com/amelietabatta/), [Iacopo Poli](https://twitter.com/iacopo_poli), and [Djamé Seddah](http://pauillac.inria.fr/~seddah/). It is named after Marcel Pagnol (with PAG standing for pré-apprentissage génératif), and was trained on the IDRIS Jean Zay supercomputer thanks to a GENCI allocation.
+
+The model was converted to the Hugging Face format by [Wissam Antoun](https://wissamantoun.com) ([ALMAnaCH](http://almanach.inria.fr/index-en.html)'s PhD student, co-supervised by [Benoît Sagot](https://pauillac.inria.fr/~sagot/) and [Djamé Seddah](http://pauillac.inria.fr/~seddah/))
+
+# Usage
+
+### Using PAGnol with Huggingface
+```python
+from transformers import pipeline
+
+generator = pipeline('text-generation', model='lightonai/pagnol-small', trust_remote_code=True)
+
+output = generator(
+    "Salut PAGnol, comment ça va ?",
+    max_length=50,
+    do_sample=True,
+    temperature=0.7,
+)[0]["generated_text"]
+
+>>> "Très bien! Les jours d’été sont là ! Bientôt les premiers festivals..."
+```
+
+### Using PAGnol with lairgpt
+Head over to our [GitHub repository](https://github.com/lightonai/lairgpt) to access our PyTorch inference code.
+Using PAGnol is as simple as running the following code:
+```python
+from lairgpt.models import PAGnol
+
+pagnol = PAGnol.small()
+pagnol("Salut PAGnol, comment ça va ?")
+
+>>> "Très bien! Les jours d’été sont là ! Bientôt les premiers festivals..."
+```
+
+# License
+PAGnol is made available under the MIT licence: by downloading the models available below, you agree with the terms of the MIT licence agreement. Under no circumstances will LightOn and/or Inria be held responsible or liable in any way for any claims, damages, losses, expenses, costs or liabilities whatsoever (including, without limitation, any direct or indirect damages for loss of profits, business interruption or loss of information) resulting or arising directly or indirectly from your use of or inability to use PAGnol.
+
+# Available Models
+- [`lightonai/pagnol-small`](https://huggingface.co/lightonai/pagnol-small): 125M parameters
+- [`lightonai/pagnol-medium`](https://huggingface.co/lightonai/pagnol-medium): 355M parameters
+- [`lightonai/pagnol-large`](https://huggingface.co/lightonai/pagnol-large): 773M parameters
+- [`lightonai/pagnol-xl`](https://huggingface.co/lightonai/pagnol-xl): 1.5B parameters
+
+# Citation
+```
+@inproceedings{launay-etal-2022-pagnol,
+    title = "{PAG}nol: An Extra-Large {F}rench Generative Model",
+    author = "Launay, Julien  and
+      Tommasone, E.l.  and
+      Pannier, Baptiste  and
+      Boniface, Fran{\c{c}}ois  and
+      Chatelain, Am{\'e}lie  and
+      Cappelli, Alessandro  and
+      Poli, Iacopo  and
+      Seddah, Djam{\'e}",
+    editor = "Calzolari, Nicoletta  and
+      B{\'e}chet, Fr{\'e}d{\'e}ric  and
+      Blache, Philippe  and
+      Choukri, Khalid  and
+      Cieri, Christopher  and
+      Declerck, Thierry  and
+      Goggi, Sara  and
+      Isahara, Hitoshi  and
+      Maegaard, Bente  and
+      Mariani, Joseph  and
+      Mazo, H{\'e}l{\`e}ne  and
+      Odijk, Jan  and
+      Piperidis, Stelios",
+    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
+    month = jun,
+    year = "2022",
+    address = "Marseille, France",
+    publisher = "European Language Resources Association",
+    url = "https://aclanthology.org/2022.lrec-1.455",
+    pages = "4275--4284",
+}
+```
+# Contact
+For research enquiries: pagnol@lighton.ai
+For business enquiries: customer.relations@lighton.ai

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu",
+  "add_prefix_space": true,
+  "architectures": [
+    "GPT2Model"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522744484cd222a0a30c2c2b383c5d64efe7b2b76522327d8e6341d220c8c45e
+size 510407273