Upload 7 files
Browse files- config.json +24 -0
- curf_architecture.json +10 -0
- merges.txt +0 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "text_to_cursor",
|
| 3 |
+
"architecture": "TextToCursorModel",
|
| 4 |
+
"encoder_type": "transformer",
|
| 5 |
+
"decoder_type": "transformer",
|
| 6 |
+
"source": "factorstudios/CURF",
|
| 7 |
+
"vocab_size": 50257,
|
| 8 |
+
"d_model": 2048,
|
| 9 |
+
"d_ff": 8192,
|
| 10 |
+
"num_encoder_layers": 12,
|
| 11 |
+
"num_decoder_layers": 6,
|
| 12 |
+
"num_heads": 32,
|
| 13 |
+
"head_dim": 64,
|
| 14 |
+
"cursor_dim": 2048,
|
| 15 |
+
"attention_dropout": 0.1,
|
| 16 |
+
"feed_forward_dropout": 0.1,
|
| 17 |
+
"activation": "relu",
|
| 18 |
+
"max_position_embeddings": 10000,
|
| 19 |
+
"layer_norm_eps": 1e-06,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"output_hidden_states": false,
|
| 22 |
+
"output_attentions": false,
|
| 23 |
+
"notes": "Downloaded from factorstudios/CURF. vocab_size=50257 matches GPT-2."
|
| 24 |
+
}
|
curf_architecture.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 50257,
|
| 3 |
+
"d_model": 2048,
|
| 4 |
+
"nlayers": 12,
|
| 5 |
+
"nhead": 32,
|
| 6 |
+
"head_dim": 64,
|
| 7 |
+
"cursor_dim": 2048,
|
| 8 |
+
"total_params": 1130610692,
|
| 9 |
+
"total_params_M": 1130.610692
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|