Initial upload of CarsonTalk 2.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 17418
+}

carson_model_final_weights.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695dc1afbc8dd07b8083bdf33e8e7f1c8d7f4c94946dd193f1eae9d1aa7f7798
+size 171943913

config.json

@@ -0,0 +1,9 @@
+{
+  "architectures": ["MiniTransformer"],
+  "vocab_size": 32000,
+  "hidden_size": 384,
+  "num_hidden_layers": 6,
+  "num_attention_heads": 8,
+  "max_position_embeddings": 512,
+  "model_type": "gpt2"
+}

modeling_minitransformer.py

@@ -0,0 +1,22 @@
+import torch
+import torch.nn as nn
+from torch.nn import CrossEntropyLoss
+
+class MiniTransformer(nn.Module):
+    def __init__(self, vocab_size, hidden_dim):
+        super().__init__()
+        self.embed = nn.Embedding(vocab_size, hidden_dim)
+        self.transformer = nn.Transformer(hidden_dim, nhead=8, num_encoder_layers=6)
+        self.out = nn.Linear(hidden_dim, vocab_size)
+
+    def forward(self, input_ids, attention_mask=None, labels=None):
+        x = self.embed(input_ids)
+        x = self.transformer(x, x)
+        logits = self.out(x)
+        loss = None
+        if labels is not None:
+            shift_logits = logits[:, :-1, :].contiguous()
+            shift_labels = labels[:, 1:].contiguous()
+            loss_fct = CrossEntropyLoss()
+            loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
+        return {"loss": loss, "logits": logits}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17418": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<unk>"
+}