init

README.md

@@ -0,0 +1,69 @@
+---
+language: ti
+license: mit
+library_name: transformers
+tags:
+- tigrinya
+- gpt2
+- text-generation
+metrics:
+- perplexity
+- loss
+pipeline_tag: text-generation
+model-index:
+- name: gpt2-tigrinya-medium
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    metrics:
+    - name: Perplexity
+      type: perplexity
+      value: 37.35
+    - name: Training Loss
+      type: loss
+      value: 3.03
+---
+
+# Model Card for GPT-2 Tigrinya Medium
+
+## Model Summary
+This is a GPT-2 model trained from scratch on Tigrinya text data. It was trained on 20 million tokens, primarily from news sources. The model is specifically designed for generating Tigrinya text using the Hugging Face Transformers library.
+
+#### Model Description
+- Model type: GPT-2
+- Language: Tigrinya (ትግርኛ)
+- Finetuned from model: Trained from scratch (no pre-training)
+
+#### Model Architecture
+- Parameters: 42.6M
+- Context Window: 128 tokens
+- **Vocabulary Size:** 52,000
+
+#### Training Details
+- Training regime: fp16 mixed precision
+- Number of Epochs: 12
+- Batch Size: 4 (with gradient accumulation steps of 8)
+- Learning Rate: 5e-4
+
+#### Evaluation
+- Training Perplexity: 37.35
+- Training Loss: 3.03
+
+#### Usage
+
+```python
+from transformers import pipeline
+# Load the model
+generator = pipeline('text-generation', model='luel/gpt2-tigrinya-medium')
+
+prompt = "ክልል ትግራይ"
+# Generate text
+text = generator(prompt, max_length=100)[0]['generated_text']
+print(text)
+```
+
+#### Limitations
+- Limited context window of 128 tokens.
+- Best suited for medium-length Tigrinya text generation.
+- Outputs should be reviewed for accuracy.