Upload folder using huggingface_hub
Browse files- added_tokens.json +16 -0
- config.json +50 -0
- generation_config.json +13 -0
- model.safetensors +3 -0
- special_tokens_map.json +32 -0
- tokenizer.model +3 -0
- tokenizer_config.json +146 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<eop>": 151334,
|
| 3 |
+
"<sop>": 151333,
|
| 4 |
+
"<|assistant|>": 151337,
|
| 5 |
+
"<|begin_of_image|>": 151339,
|
| 6 |
+
"<|begin_of_video|>": 151341,
|
| 7 |
+
"<|end_of_image|>": 151340,
|
| 8 |
+
"<|end_of_video|>": 151342,
|
| 9 |
+
"<|endoftext|>": 151329,
|
| 10 |
+
"<|observation|>": 151338,
|
| 11 |
+
"<|system|>": 151335,
|
| 12 |
+
"<|user|>": 151336,
|
| 13 |
+
"[MASK]": 151330,
|
| 14 |
+
"[gMASK]": 151331,
|
| 15 |
+
"[sMASK]": 151332
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "THUDM/glm-4-9b-chat",
|
| 3 |
+
"add_bias_linear": false,
|
| 4 |
+
"add_qkv_bias": true,
|
| 5 |
+
"apply_query_key_layer_scaling": true,
|
| 6 |
+
"apply_residual_connection_post_layernorm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"ChatGLMForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"attention_softmax_in_fp32": true,
|
| 12 |
+
"auto_map": {
|
| 13 |
+
"AutoConfig": "THUDM/glm-4-9b-chat--configuration_chatglm.ChatGLMConfig",
|
| 14 |
+
"AutoModel": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 15 |
+
"AutoModelForCausalLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 16 |
+
"AutoModelForSeq2SeqLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 17 |
+
"AutoModelForSequenceClassification": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForSequenceClassification"
|
| 18 |
+
},
|
| 19 |
+
"bias_dropout_fusion": true,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"eos_token_id": [
|
| 22 |
+
151329,
|
| 23 |
+
151336,
|
| 24 |
+
151338
|
| 25 |
+
],
|
| 26 |
+
"ffn_hidden_size": 16,
|
| 27 |
+
"fp32_residual_connection": false,
|
| 28 |
+
"hidden_dropout": 0.0,
|
| 29 |
+
"hidden_size": 8,
|
| 30 |
+
"kv_channels": 2,
|
| 31 |
+
"layernorm_epsilon": 1.5625e-07,
|
| 32 |
+
"model_type": "chatglm",
|
| 33 |
+
"multi_query_attention": true,
|
| 34 |
+
"multi_query_group_num": 2,
|
| 35 |
+
"num_attention_heads": 4,
|
| 36 |
+
"num_hidden_layers": 2,
|
| 37 |
+
"num_layers": 2,
|
| 38 |
+
"original_rope": true,
|
| 39 |
+
"pad_token_id": 151329,
|
| 40 |
+
"padded_vocab_size": 151552,
|
| 41 |
+
"post_layer_norm": true,
|
| 42 |
+
"rmsnorm": true,
|
| 43 |
+
"rope_ratio": 500,
|
| 44 |
+
"seq_length": 131072,
|
| 45 |
+
"tie_word_embeddings": false,
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"transformers_version": "4.38.2",
|
| 48 |
+
"use_cache": true,
|
| 49 |
+
"vocab_size": 151552
|
| 50 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151329,
|
| 5 |
+
151336,
|
| 6 |
+
151338
|
| 7 |
+
],
|
| 8 |
+
"max_length": 128000,
|
| 9 |
+
"pad_token_id": 151329,
|
| 10 |
+
"temperature": 0.8,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.38.2"
|
| 13 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fa45eed75dcb74cd011870d716fb1a7438ee8246aaf58b9999e025c5b3bfd5f
|
| 3 |
+
size 4854314
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"[MASK]",
|
| 5 |
+
"[gMASK]",
|
| 6 |
+
"[sMASK]",
|
| 7 |
+
"<sop>",
|
| 8 |
+
"<eop>",
|
| 9 |
+
"<|system|>",
|
| 10 |
+
"<|user|>",
|
| 11 |
+
"<|assistant|>",
|
| 12 |
+
"<|observation|>",
|
| 13 |
+
"<|begin_of_image|>",
|
| 14 |
+
"<|end_of_image|>",
|
| 15 |
+
"<|begin_of_video|>",
|
| 16 |
+
"<|end_of_video|>"
|
| 17 |
+
],
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|endoftext|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": {
|
| 26 |
+
"content": "<|endoftext|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
}
|
| 32 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
|
| 3 |
+
size 2623634
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"151329": {
|
| 4 |
+
"content": "<|endoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"151330": {
|
| 12 |
+
"content": "[MASK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"151331": {
|
| 20 |
+
"content": "[gMASK]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"151332": {
|
| 28 |
+
"content": "[sMASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"151333": {
|
| 36 |
+
"content": "<sop>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"151334": {
|
| 44 |
+
"content": "<eop>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"151335": {
|
| 52 |
+
"content": "<|system|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"151336": {
|
| 60 |
+
"content": "<|user|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"151337": {
|
| 68 |
+
"content": "<|assistant|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"151338": {
|
| 76 |
+
"content": "<|observation|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"151339": {
|
| 84 |
+
"content": "<|begin_of_image|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"151340": {
|
| 92 |
+
"content": "<|end_of_image|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"151341": {
|
| 100 |
+
"content": "<|begin_of_video|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"151342": {
|
| 108 |
+
"content": "<|end_of_video|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
}
|
| 115 |
+
},
|
| 116 |
+
"additional_special_tokens": [
|
| 117 |
+
"<|endoftext|>",
|
| 118 |
+
"[MASK]",
|
| 119 |
+
"[gMASK]",
|
| 120 |
+
"[sMASK]",
|
| 121 |
+
"<sop>",
|
| 122 |
+
"<eop>",
|
| 123 |
+
"<|system|>",
|
| 124 |
+
"<|user|>",
|
| 125 |
+
"<|assistant|>",
|
| 126 |
+
"<|observation|>",
|
| 127 |
+
"<|begin_of_image|>",
|
| 128 |
+
"<|end_of_image|>",
|
| 129 |
+
"<|begin_of_video|>",
|
| 130 |
+
"<|end_of_video|>"
|
| 131 |
+
],
|
| 132 |
+
"auto_map": {
|
| 133 |
+
"AutoTokenizer": [
|
| 134 |
+
"THUDM/glm-4-9b-chat--tokenization_chatglm.ChatGLM4Tokenizer",
|
| 135 |
+
null
|
| 136 |
+
]
|
| 137 |
+
},
|
| 138 |
+
"clean_up_tokenization_spaces": false,
|
| 139 |
+
"do_lower_case": false,
|
| 140 |
+
"eos_token": "<|endoftext|>",
|
| 141 |
+
"model_max_length": 128000,
|
| 142 |
+
"pad_token": "<|endoftext|>",
|
| 143 |
+
"padding_side": "left",
|
| 144 |
+
"remove_space": false,
|
| 145 |
+
"tokenizer_class": "ChatGLM4Tokenizer"
|
| 146 |
+
}
|