初始化项目，由ModelHub XC社区提供模型

Model: mrm8488/spanish-gpt2
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
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+language: es
+tags:
+- GPT-2
+datasets:
+ - large_spanish_corpus
+widgets:
+- text: "Érase un vez un"
+
+license: mit
+
+---
+# Spanish GPT-2 trained on [large_spanish_corpus](https://huggingface.co/datasets/viewer/?dataset=large_spanish_corpus)
+
+This is a Spanish GPT-2 model trained from scratch on the [large_spanish_corpus](https://huggingface.co/datasets/viewer/?dataset=large_spanish_corpus) aka BETO's corpus with [Flax](https://github.com/google/flax)
+This is part of the
+[Flax/Jax Community Week](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104), organised by [HuggingFace](https://huggingface.co/) and TPU usage sponsored by Google.
+## Dataset
+The dataset is about 20 GB. 95% of the data was used for training and the rest 5% for validation.
+
+## Metrics (on evaluation dataset)
+
+- Loss: 2.413
+- Perplexity: 11.36
+
+## Team members
+- Manuel Romero ([mrm8488](https://huggingface.co/mrm8488))
+- María Grandury ([mariagrandury](https://huggingface.co/))
+- Pablo González de Prado ([Pablogps](https://huggingface.co/Pablogps))
+- Daniel Vera ([daveni](https://huggingface.co/daveni))
+- Sri Lakshmi ([srisweet](https://huggingface.co/srisweet))
+- José Posada ([jdposa](https://huggingface.co/jdposa))
+- Santiago Hincapie ([shpotes](https://huggingface.co/shpotes))
+- Jorge ([jorgealro](https://huggingface.co/jorgealro))
+
+
+## Useful links
+- [Community Week timeline](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104#summary-timeline-calendar-6)
+- [Community Week README](https://github.com/huggingface/transformers/blob/master/examples/research_projects/jax-projects/README.md)
+- [Community Week thread](https://discuss.huggingface.co/t/pretrain-gpt2-from-scratch-in-spanish/7086/8)

added_tokens.json

@@ -0,0 +1 @@
+{"<|endoftext|>": 50265}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "/content/spanish-gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "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": 0.0,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

events.out.tfevents.1625645434.t1v-n-c632aea2-w-0.400553.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e58e8edc8a0c3058acb534d7f32902a9972fd690839f852b5ca9fa74751a89
+size 40

events.out.tfevents.1625646194.t1v-n-c632aea2-w-0.402619.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c204b0be5dacf7426d926ea840e25cef82398e613d100699b611071d601fa7
+size 40

events.out.tfevents.1625665214.t1v-n-c632aea2-w-0.13918.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58f7bb22d1ac3c7de24543921a9b1d6ebb7962199761097333a5277fab91182
+size 10393677

events.out.tfevents.1625825648.t1v-n-c632aea2-w-0.157864.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e718cc18eb3ddf4a3ddb45994afe9840337347ba8ba8ec1641ae2aa2949fc3
+size 2239188

events.out.tfevents.1625864160.t1v-n-c632aea2-w-0.13475.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7087139ce60fdb5da3eb0d775c7243c537c6de360913bbcbce8c85dcefe2da
+size 2239188

events.out.tfevents.1626078407.t1v-n-c632aea2-w-0.147303.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7d45ce009dc4537e4a641cc2e8424da39173929906d4fb6ecb2c014a7b8853
+size 20628067

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d7717a802f2f5c9a9c46338d14711866dd2d8b7050e5e80ea4d0bb463e4b6c
+size 497764120

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6112f38d8634a0107c5e07c16160b75fec3f918f41cb0415ca557b61df59d312
+size 510359598

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998272a08554353fda6f62096843df58fe0133d543c33f79a53b0dd7c5c9a169
+size 510401385

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "mrm8488/spanish-gpt2", "tokenizer_class": "GPT2Tokenizer"}