Push wandb artifact dalle-mini/dalle-mini/mega-1:v16
Browse files- config.json +54 -0
- flax_model.msgpack +3 -0
- merges.txt +0 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"eBart"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 16385,
|
9 |
+
"d_model": 2048,
|
10 |
+
"decoder_attention_heads": 32,
|
11 |
+
"decoder_ffn_dim": 4096,
|
12 |
+
"decoder_layerdrop": 0.0,
|
13 |
+
"decoder_layers": 24,
|
14 |
+
"decoder_start_token_id": 16384,
|
15 |
+
"do_sample": true,
|
16 |
+
"dropout": 0.0,
|
17 |
+
"encoder_attention_heads": 32,
|
18 |
+
"encoder_ffn_dim": 4096,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 24,
|
21 |
+
"encoder_vocab_size": 50272,
|
22 |
+
"eos_token_id": 16385,
|
23 |
+
"force_ln_scale": false,
|
24 |
+
"gradient_checkpointing": true,
|
25 |
+
"image_length": 256,
|
26 |
+
"image_vocab_size": 16415,
|
27 |
+
"init_std": 0.01,
|
28 |
+
"is_encoder_decoder": true,
|
29 |
+
"ln_positions": "normformer",
|
30 |
+
"ln_type": "layernorm",
|
31 |
+
"max_length": 257,
|
32 |
+
"max_text_length": 64,
|
33 |
+
"min_length": 257,
|
34 |
+
"model_type": "dallebart",
|
35 |
+
"normalize_text": true,
|
36 |
+
"pad_token_id": 16385,
|
37 |
+
"scale_embedding": false,
|
38 |
+
"sinkhorn_iters": 1,
|
39 |
+
"tau_init": 0.05,
|
40 |
+
"tie_word_embeddings": false,
|
41 |
+
"transformers_version": "4.20.0.dev0",
|
42 |
+
"use_absolute_position_embeddings": true,
|
43 |
+
"use_alibi": false,
|
44 |
+
"use_bias": false,
|
45 |
+
"use_cache": true,
|
46 |
+
"use_cosine_attention": false,
|
47 |
+
"use_deepnet_scaling": false,
|
48 |
+
"use_final_ln_decoder": true,
|
49 |
+
"use_final_ln_encoder": true,
|
50 |
+
"use_glu": true,
|
51 |
+
"use_head_scale": false,
|
52 |
+
"use_scan": true,
|
53 |
+
"use_swin_position_embeddings": false
|
54 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a6c84b02cff45f7257283dbc7f2e4c403950ef146d9f0c9f5e6b9848b9602c
|
3 |
+
size 10350086035
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "boris/dalle-mini-tokenizer", "use_fast": true, "tokenizer_class": "DalleBartTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|