Upload 3 files

README.md

@@ -0,0 +1,33 @@
+# Mini GPT1 Clone
+
+This is a decoder-only transformer model (GPT1-style) trained from scratch using PyTorch.
+
+## Model Details
+
+- **Architecture**: Decoder-only Transformer
+- **Layers**: 6
+- **Embedding Size**: 512
+- **Heads**: 8
+- **Feedforward Dim**: 2048
+- **Sequence Length**: 256
+- **Vocab Size**: 35,000
+
+## Tokenizer
+
+Trained using `ByteLevelBPETokenizer` from the `tokenizers` library.
+
+## Inference Example
+
+```python
+from transformers import PreTrainedTokenizerFast, AutoModelForCausalLM
+import torch
+
+tokenizer = PreTrainedTokenizerFast(tokenizer_file="tokenizer/tokenizer.json")
+model = AutoModelForCausalLM.from_pretrained("dilip025/mini-gpt1")
+
+prompt = "Once upon a time,"
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+outputs = model.generate(input_ids, max_length=50)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+License
+MIT

tokenizer_config.json

@@ -1,23 +1,8 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "30000": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}
+    "add_prefix_space": true,
+    "model_max_length": 256,
+    "tokenizer_class": "PreTrainedTokenizerFast",
+    "unk_token": "<unk>",
+    "bos_token": "<s>",
+    "eos_token": "</s>"
+}