initial commit

README.md

@@ -0,0 +1,65 @@
+---
+language: 
+- sr
+thumbnail: https://huggingface.co/macedonizer/sr-gpt2/desanka-maksimovic.jpeg
+license: Apache 2.0
+datasets:
+- wiki-sr
+---
+
+# sr-gpt2
+Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large
+Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in
+[this paper](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)
+and first released at [this page](https://openai.com/blog/better-language-models/).
+
+## Model description
+sr-gpt2 is a transformers model pretrained on a very large corpus of Serbian data in a self-supervised fashion. This
+means it was pretrained on the raw texts only, with no humans labeling them in any way (which is why it can use lots
+of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely,
+it was trained to guess the next word in sentences.
+More precisely, inputs are sequences of the continuous text of a certain length and the targets are the same sequence,
+shifted one token (word or piece of the word) to the right. The model uses internally a mask-mechanism to make sure the
+predictions for the token `i` only uses the inputs from `1` to `i` but not the future tokens.
+This way, the model learns an inner representation of the Macedonian language that can then be used to extract features
+useful for downstream tasks. The model is best at what it was pretrained for, however, which is generating texts from a
+prompt.
+
+### How to use
+Here is how to use this model to get the features of a given text in PyTorch:
+
+import random \
+from transformers import AutoTokenizer, AutoModelWithLMHead
+
+tokenizer = AutoTokenizer.from_pretrained('macedonizer/sr-gpt2') \
+model = AutoModelWithLMHead.from_pretrained('macedonizer/sr-gpt2')
+
+input_text = 'Ја сам био '
+
+if len(input_text) == 0: \
+    encoded_input = tokenizer(input_text, return_tensors="pt") \
+    output = model.generate( \
+        bos_token_id=random.randint(1, 50000), \
+        do_sample=True, \
+        top_k=50, \
+        max_length=1024, \
+        top_p=0.95, \
+        num_return_sequences=1, \
+    ) \
+else: \
+    encoded_input = tokenizer(input_text, return_tensors="pt") \
+    output = model.generate( \
+        **encoded_input, \
+        bos_token_id=random.randint(1, 50000), \
+        do_sample=True, \
+        top_k=50, \
+        max_length=1024, \
+        top_p=0.95, \
+        num_return_sequences=1, \
+    )
+
+decoded_output = [] \
+for sample in output: \
+    decoded_output.append(tokenizer.decode(sample, skip_special_tokens=True))
+
+print(decoded_output)

config.json

@@ -0,0 +1,30 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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,
+  "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,
+  "transformers_version": "4.6.1",
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f9aa53870e53cc45965b87137b69dd8ed72e7aac32222ec0fa22f2bf137fe8
+size 515758313

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c35c1f76fff922e01f442bab83c8f1c3d114a87966eed2ce5e6aaee437ccdd04
+size 2479