Upload folder using huggingface_hub

README.md

@@ -0,0 +1,7 @@
+---
+library_name: pytorch
+tags: [gpt2, llm, scratch-implementation]
+license: mit
+---
+# Custom GPT-2 (124M)
+Trained from scratch. Final Val Loss: 4.2818

config.json

@@ -0,0 +1,16 @@
+{
+  "architectures": [
+    "GPTModel"
+  ],
+  "model_type": "gpt2",
+  "vocab_size": 50257,
+  "n_positions": 1024,
+  "n_embd": 768,
+  "n_layer": 12,
+  "n_head": 12,
+  "resid_pdrop": 0.1,
+  "activation_function": "gelu_new",
+  "initializer_range": 0.02,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c7dc88b8666d3f877144bccb7a03bc311b32c8fd43b8d1fca013674d1e7043
+size 652051984

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e7f28203b722cc5059542e2ea11b8f8dead9635c5828504d9eb7d2814db726
+size 652081351

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}