Hugging Face's logo

Tongjilibo
/
bert4torch_config

Model card Files Community
Tongjilibo commited on
Commit
0b80d89
•
1 Parent(s): f3c8733

修改tie_emb_prj_weight为tie_word_embeddings

Browse files
Files changed (12) hide show
  1. bert-base-chinese/bert4torch_config.json +1 -1
  2. bloom-560m/bert4torch_config.json +1 -1
  3. bloomz-560m/bert4torch_config.json +1 -1
  4. chatglm-6b-int4/bert4torch_config.json +1 -1
  5. chatglm-6b-int8/bert4torch_config.json +1 -1
  6. chatglm-6b-v0.1.0/bert4torch_config.json +1 -1
  7. chatglm-6b/bert4torch_config.json +1 -1
  8. chatglm2-6b-32k/bert4torch_config.json +1 -1
  9. chatglm2-6b-int4/bert4torch_config.json +1 -1
  10. chatglm2-6b/bert4torch_config.json +1 -1
  11. chatglm3-6b-32k/bert4torch_config.json +1 -1
  12. chatglm3-6b/bert4torch_config.json +1 -1
bert-base-chinese/bert4torch_config.json CHANGED
@@ -13,5 +13,5 @@
13
  "pad_token_id": 0,
14
  "type_vocab_size": 2,
15
  "vocab_size": 21128,
16
- "tie_emb_prj_weight": true
17
  }
 
13
  "pad_token_id": 0,
14
  "type_vocab_size": 2,
15
  "vocab_size": 21128,
16
+ "tie_word_embeddings": true
17
  }
bloom-560m/bert4torch_config.json CHANGED
@@ -22,6 +22,6 @@
22
  "vocab_size": 250880,
23
  "segment_vocab_size": 0,
24
  "pre_layernorm": true,
25
- "tie_emb_prj_weight": true,
26
  "model": "bloom"
27
  }
 
22
  "vocab_size": 250880,
23
  "segment_vocab_size": 0,
24
  "pre_layernorm": true,
25
+ "tie_word_embeddings": true,
26
  "model": "bloom"
27
  }
bloomz-560m/bert4torch_config.json CHANGED
@@ -22,6 +22,6 @@
22
  "vocab_size": 250880,
23
  "segment_vocab_size": 0,
24
  "pre_layernorm": true,
25
- "tie_emb_prj_weight": true,
26
  "model": "bloom"
27
  }
 
22
  "vocab_size": 250880,
23
  "segment_vocab_size": 0,
24
  "pre_layernorm": true,
25
+ "tie_word_embeddings": true,
26
  "model": "bloom"
27
  }
chatglm-6b-int4/bert4torch_config.json CHANGED
@@ -18,7 +18,7 @@
18
  "segment_vocab_size": 0,
19
  "skip_init": true,
20
  "rope_rank": "updown",
21
- "tie_emb_prj_weight": false,
22
  "quantization_bit": 4,
23
  "quantization_method": "cpm_kernels",
24
  "target_modules": ["q", "k", "v", "o", "intermediateDense", "outputDense"],
 
18
  "segment_vocab_size": 0,
19
  "skip_init": true,
20
  "rope_rank": "updown",
21
+ "tie_word_embeddings": false,
22
  "quantization_bit": 4,
23
  "quantization_method": "cpm_kernels",
24
  "target_modules": ["q", "k", "v", "o", "intermediateDense", "outputDense"],
chatglm-6b-int8/bert4torch_config.json CHANGED
@@ -21,6 +21,6 @@
21
  "quantization_bit": 8,
22
  "quantization_method": "cpm_kernels",
23
  "target_modules": ["q", "k", "v", "o", "intermediateDense", "outputDense"],
24
- "tie_emb_prj_weight": false,
25
  "generation_config": {"max_length": 2048}
26
  }
 
21
  "quantization_bit": 8,
22
  "quantization_method": "cpm_kernels",
23
  "target_modules": ["q", "k", "v", "o", "intermediateDense", "outputDense"],
24
+ "tie_word_embeddings": false,
25
  "generation_config": {"max_length": 2048}
26
  }
chatglm-6b-v0.1.0/bert4torch_config.json CHANGED
@@ -18,6 +18,6 @@
18
  "segment_vocab_size": 0,
19
  "skip_init": true,
20
  "rope_rank": "updown",
21
- "tie_emb_prj_weight": false,
22
  "generation_config": {"max_length": 2048}
23
  }
 
18
  "segment_vocab_size": 0,
19
  "skip_init": true,
20
  "rope_rank": "updown",
21
+ "tie_word_embeddings": false,
22
  "generation_config": {"max_length": 2048}
23
  }
chatglm-6b/bert4torch_config.json CHANGED
@@ -18,6 +18,6 @@
18
  "segment_vocab_size": 0,
19
  "skip_init": true,
20
  "rope_rank": "updown",
21
- "tie_emb_prj_weight": false,
22
  "generation_config": {"max_length": 2048}
23
  }
 
18
  "segment_vocab_size": 0,
19
  "skip_init": true,
20
  "rope_rank": "updown",
21
+ "tie_word_embeddings": false,
22
  "generation_config": {"max_length": 2048}
23
  }
chatglm2-6b-32k/bert4torch_config.json CHANGED
@@ -11,7 +11,7 @@
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
- "tie_emb_prj_weight": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
 
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
+ "tie_word_embeddings": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
chatglm2-6b-int4/bert4torch_config.json CHANGED
@@ -11,7 +11,7 @@
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
- "tie_emb_prj_weight": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
 
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
+ "tie_word_embeddings": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
chatglm2-6b/bert4torch_config.json CHANGED
@@ -11,7 +11,7 @@
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
- "tie_emb_prj_weight": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
 
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
+ "tie_word_embeddings": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
chatglm3-6b-32k/bert4torch_config.json CHANGED
@@ -11,7 +11,7 @@
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
- "tie_emb_prj_weight": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
 
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
+ "tie_word_embeddings": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 2,
17
  "rmsnorm": true,
chatglm3-6b/bert4torch_config.json CHANGED
@@ -11,7 +11,7 @@
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
- "tie_emb_prj_weight": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 0,
17
  "rmsnorm": true,
 
11
  "segment_vocab_size": 0,
12
  "multi_query_group_num": 2,
13
  "skip_init": true,
14
+ "tie_word_embeddings": false,
15
  "eos_token_id": 2,
16
  "pad_token_id": 0,
17
  "rmsnorm": true,