初始化项目，由ModelHub XC社区提供模型

Model: Ferch423/gpt2-small-portuguese-wikipediabio
Source: Original Platform

.gitattributes

@@ -0,0 +1,9 @@
+*.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

README.md

@@ -0,0 +1,23 @@
+---
+language: "pt"
+tags:
+- pt
+- wikipedia
+- gpt2
+- finetuning
+datasets:
+- wikipedia
+widget:
+- "André Um"
+- "Maria do Santos"
+- "Roberto Carlos"
+licence: "mit"
+
+---
+
+# GPT2-SMALL-PORTUGUESE-WIKIPEDIABIO
+
+
+This is a finetuned model version of gpt2-small-portuguese(https://huggingface.co/pierreguillou/gpt2-small-portuguese) by pierreguillou.
+
+It was trained on a person abstract dataset extracted from DBPEDIA (over 100000 people's abstracts). The model is intended as a simple and fun experiment for generating texts abstracts based on ordinary people's names.  

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "pierreguillou/gpt2-small-portuguese",
+  "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
+    }
+  },
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results_clm.txt

@@ -0,0 +1 @@
+perplexity = 7.942718614428892

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ecc0eecc04ccf760053d55e23a7c74ef72ebacaaaa9f0af902046aecdd2ce9
+size 497764120

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8ce3e8dd373bcc088af0d797cd9ef39474e21616e9e0f23cb757fcd34f0797
+size 510378682

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "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, "full_tokenizer_file": null, "name_or_path": "pierreguillou/gpt2-small-portuguese", "errors": "replace"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3394eb82df3bedcf80da8eb73488043f1df4ad22c795dfe1f80c07f23634b6f2
+size 1522