Initial push (custom nn.Module)

config.json

@@ -0,0 +1,18 @@
+{
+  "model_kwargs": {
+    "model_name_or_path": "gpt2",
+    "model_cache_dir": "data/model_cache",
+    "tokenizer_cache_dir": "data/model_cache",
+    "tokenizer_name_or_path": "gpt2",
+    "embedding_dim": 2048,
+    "num_layers": 22,
+    "num_heads": 16,
+    "num_kv_heads": 4,
+    "ffn_dim_multiplier": 4.0,
+    "dropout": 0.1,
+    "use_flash_attention_2": true,
+    "learning_rate": 0.0003,
+    "weight_decay": 0.1,
+    "max_length": 1024
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73da18ae8ef5d0f0f840d3250d59c127cc9e540223e76d2cd371169205eab20
+size 4379938818

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "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,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}