初始化项目，由ModelHub XC社区提供模型

Model: dbddv01/gpt2-french-small
Source: Original Platform

.gitattributes

@@ -0,0 +1,18 @@
+*.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
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+language: "fr"
+
+tags:
+- french
+- gpt2
+- model
+---
+
+A small french language model for french text generation (and possibly more NLP tasks...)
+
+**Introduction**
+
+This french gpt2 model is based on openai GPT-2 small model.
+
+It was trained on a <b>very small (190Mb) dataset </b> from french wikipedia using Transfer Learning and Fine-tuning techniques in just over a day, on one Colab pro with 1GPU 16GB.
+
+It was created applying the recept of <b>Pierre Guillou</b>
+
+See https://medium.com/@pierre_guillou/faster-than-training-from-scratch-fine-tuning-the-english-gpt-2-in-any-language-with-hugging-f2ec05c98787
+
+It is a proof-of-concept that makes possible to get a language model in any language with low ressources.
+
+It was fine-tuned from the English pre-trained GPT-2 small using the Hugging Face libraries (Transformers and Tokenizers) wrapped into the fastai v2 Deep Learning framework. All the fine-tuning fastai v2 techniques were used.
+
+It is now available on Hugging Face. For further information or requests, please go to "Faster than training from scratch — Fine-tuning the English GPT-2 in any language with Hugging Face and fastai v2 (practical case with Portuguese)".
+
+Model migth be improved by using larger dataset under larger powerful training infrastructure. At least this one can be used for small finetuning experimentation (i.e with aitextgen).
+
+PS : I've lost the metrics but it speaks french with some minor grammar issues, coherence of text is somehow limited.   

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/root/.fastai/data/frwiki/gpt2-small-french",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.2.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed44beb48fc72279beb2789a2c6913aa68f062aa92a1247f97b6eda6a10f670f
+size 497764120

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60372bf77287074af8ddeb2889efb4b38d71c66ee0863dc0e3d04c4364da5bf
+size 510359598

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2ceecbf087e754f14e02686a9f508c427f49e75141de8f82a5fc71c04cbc05
+size 510406637

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "pad_token": "<|endoftext|>", "special_tokens_map_file": null, "name_or_path": "/root/.fastai/data/frwiki/ByteLevelBPE_tokenizer_pt", "errors": "replace"}