Initial commit

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 16000
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 16000,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 16000,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 384,
+  "n_head": 6,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 128,
+  "pad_token_id": 16000,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 16000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 16000,
+  "eos_token_id": 16000,
+  "pad_token_id": 16000,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44acda5fc5c4f11c4676483c2b3f6b69af2dad5a12dab0caf65b18e1859c42cd
+size 67387730

readme.md

@@ -0,0 +1,41 @@
+language: ti
+tags:
+- tigrinya
+- gpt2
+- text-generation
+---
+
+# GPT-2 for Tigrinya Language
+
+This repository contains a GPT-2 model trained from scratch on Tigrinya text data. The model was trained using the Hugging Face Transformers library.
+
+## Model Details
+
+- Model Type: GPT-2
+- Language: Tigrinya
+- Vocabulary Size: 16000
+- Maximum Length: 128
+- Model Size: Small
+- Number of Parameters: 33,523,200
+
+## Training Details
+
+- Number of Epochs: 12
+- Batch Size: 1 (with gradient accumulation steps of 4)
+- Learning Rate: 5e-4
+
+## Dataset Statistics
+- Total number of words: 16061839
+- Total number of unique words: 458901
+
+## Usage
+
+```python
+from transformers import pipeline
+
+# Load the model
+generator = pipeline('text-generation', model='luel/gpt2-tigrinya-small')
+
+# Generate text
+text = generator("ትግራይ", max_length=60)
+print(text)

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3777a317bf341e421d34ab5c85e2f26e4745322ade7e92ac2ba07678fd929786
+size 4344