coincheung commited on
Commit
96a76ce
1 Parent(s): 4f40e62
config.json CHANGED
@@ -29,5 +29,5 @@
29
  "transformers_version": "4.28.1",
30
  "unk_token_id": 0,
31
  "use_cache": true,
32
- "vocab_size": 250880
33
  }
 
29
  "transformers_version": "4.28.1",
30
  "unk_token_id": 0,
31
  "use_cache": true,
32
+ "vocab_size": 156368
33
  }
pytorch_model-00001-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a017493ebc9f9bd7b112b946db7c68d56fdbab4be1b8fed225f962d5018827d8
3
- size 9890195322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a21130a585f909363ee42cb9d4a15246c9c35c146e47db1f21cdc30900a9e8
3
+ size 9873310944
pytorch_model-00002-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4c424ef308b6e8476cc5ea20b3935d00fac1946ba44e53452cd3fd604d16892
3
- size 4519953722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae898f403cbc546e3d6752456ba9251a8e99ab5002e3d6cc144c5cd909c320c6
3
+ size 4771571788
pytorch_model.bin.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 14410022912
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "pytorch_model-00002-of-00002.bin",
@@ -176,8 +176,8 @@
176
  "transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
177
  "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
178
  "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
179
- "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
180
- "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
181
  "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
182
  "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
  "transformer.h.21.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
 
1
  {
2
  "metadata": {
3
+ "total_size": 14644756480
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "pytorch_model-00002-of-00002.bin",
 
176
  "transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
177
  "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
178
  "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
179
+ "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
180
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
181
  "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
182
  "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
  "transformer.h.21.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff