init

.gitattributes

@@ -15,3 +15,4 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.h5 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,24 @@
+Model card for RoGPT2-base
+
+---
+language: 
+- ro
+---
+
+# RoGPT2: Romanian GPT2 for text generation
+
+All models are available:
+* [RoBERT-base](https://huggingface.co/readerbench/RoGPT2-base)
+* [RoBERT-medium](https://huggingface.co/readerbench/RoGPT2-medium)
+* [RoBERT-large](https://huggingface.co/readerbench/RoGPT2-large)
+
+#### How to use
+```python
+~~from transformers import AutoTokenizer, TFAutoModelWithLMHead
+
+tokenizer = AutoTokenizer.from_pretrained('readerbench/RoGPT2-base')
+model = TFAutoModelWithLMHead.from_pretrained('readerbench/RoGPT2-base')
+inputs = tokenizer.encode("Este o zi de vara", return_tensors='tf')
+text = model.generate(inputs, max_length=1024,  no_repeat_ngram_size=2)
+print(tokenizer.decode(text[0]))~~
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "model/base",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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": "4.5.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

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}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433a00b42261edcb8a415b3ffb3a9f84ca8eb5ae79ae4ec5d4355a28db08e56b
+size 497933648

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "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, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "tokenizer"}