jacobthebanana
commited on
Added tokenizer.
Browse files- config.json +3 -3
- flax_model.msgpack +2 -2
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -0
config.json
CHANGED
@@ -7,15 +7,15 @@
|
|
7 |
"OPTForCausalLM"
|
8 |
],
|
9 |
"attention_dropout": 0.1,
|
10 |
-
"bias": false,
|
11 |
"bos_token_id": 0,
|
12 |
"do_layer_norm_before": true,
|
13 |
"dropout": 0.1,
|
|
|
14 |
"eos_token_id": 2,
|
15 |
"ffn_dim": 3072,
|
16 |
"hidden_size": 768,
|
17 |
"init_std": 0.02,
|
18 |
-
"layer_norm_elementwise_affine":
|
19 |
"layerdrop": 0.0,
|
20 |
"learned_embeddings": true,
|
21 |
"max_position_embeddings": 2048,
|
@@ -25,7 +25,7 @@
|
|
25 |
"pad_token_id": 1,
|
26 |
"scale_embeddings": false,
|
27 |
"torch_dtype": "float32",
|
28 |
-
"transformers_version": "4.
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 50000,
|
31 |
"word_embed_proj_dim": 768
|
|
|
7 |
"OPTForCausalLM"
|
8 |
],
|
9 |
"attention_dropout": 0.1,
|
|
|
10 |
"bos_token_id": 0,
|
11 |
"do_layer_norm_before": true,
|
12 |
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
"eos_token_id": 2,
|
15 |
"ffn_dim": 3072,
|
16 |
"hidden_size": 768,
|
17 |
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
"layerdrop": 0.0,
|
20 |
"learned_embeddings": true,
|
21 |
"max_position_embeddings": 2048,
|
|
|
25 |
"pad_token_id": 1,
|
26 |
"scale_embeddings": false,
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.25.1",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 50000,
|
31 |
"word_embed_proj_dim": 768
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:999a24b016e17563c41d703b32657a96928f9d9ee361dc9d623e0501807f51b6
|
3 |
+
size 250067649
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "</s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 1000000000000000019884624838656,
|
3 |
+
"name_or_path": "facebook/galactica-125m",
|
4 |
+
"special_tokens_map_file": "/content/tokenizer/special_tokens_map.json",
|
5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
6 |
+
}
|