Upload folder using huggingface_hub
Browse files- __init__.py +0 -0
- config.json +30 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +145 -0
__init__.py
ADDED
|
File without changes
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/scratch/project_465000144/dasamuel/normistral/normistral-11b-masked-post-hf-60000-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"mask_token_id": 4,
|
| 15 |
+
"max_position_embeddings": 1024000,
|
| 16 |
+
"model_type": "mistral",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 40,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pad_token_id": 3,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.44.0.dev0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 51200,
|
| 29 |
+
"n_labels": 1
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 3,
|
| 6 |
+
"transformers_version": "4.44.0.dev0"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10ff742ce17c2236ec2318cf995adc1295911b7abb22bdd6b4a0c6faaff9743c
|
| 3 |
+
size 22859907598
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"mask_token": {
|
| 31 |
+
"content": "<mask>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token_id": 0,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 3,
|
| 6 |
+
"add_bos_token": true,
|
| 7 |
+
"add_eos_token": false,
|
| 8 |
+
"add_prefix_space": false,
|
| 9 |
+
"added_tokens_decoder": {
|
| 10 |
+
"0": {
|
| 11 |
+
"content": "<unk>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false,
|
| 16 |
+
"special": true
|
| 17 |
+
},
|
| 18 |
+
"1": {
|
| 19 |
+
"content": "<s>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"special": true
|
| 25 |
+
},
|
| 26 |
+
"2": {
|
| 27 |
+
"content": "</s>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false,
|
| 32 |
+
"special": true
|
| 33 |
+
},
|
| 34 |
+
"3": {
|
| 35 |
+
"content": "<pad>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
"4": {
|
| 43 |
+
"content": "<mask>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false,
|
| 48 |
+
"special": true
|
| 49 |
+
},
|
| 50 |
+
"5": {
|
| 51 |
+
"content": "<special_0>",
|
| 52 |
+
"lstrip": false,
|
| 53 |
+
"normalized": false,
|
| 54 |
+
"rstrip": false,
|
| 55 |
+
"single_word": false,
|
| 56 |
+
"special": true
|
| 57 |
+
},
|
| 58 |
+
"6": {
|
| 59 |
+
"content": "<special_1>",
|
| 60 |
+
"lstrip": false,
|
| 61 |
+
"normalized": false,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"special": true
|
| 65 |
+
},
|
| 66 |
+
"7": {
|
| 67 |
+
"content": "<special_2>",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false,
|
| 72 |
+
"special": true
|
| 73 |
+
},
|
| 74 |
+
"8": {
|
| 75 |
+
"content": "<special_3>",
|
| 76 |
+
"lstrip": false,
|
| 77 |
+
"normalized": false,
|
| 78 |
+
"rstrip": false,
|
| 79 |
+
"single_word": false,
|
| 80 |
+
"special": true
|
| 81 |
+
},
|
| 82 |
+
"9": {
|
| 83 |
+
"content": "<special_4>",
|
| 84 |
+
"lstrip": false,
|
| 85 |
+
"normalized": false,
|
| 86 |
+
"rstrip": false,
|
| 87 |
+
"single_word": false,
|
| 88 |
+
"special": true
|
| 89 |
+
},
|
| 90 |
+
"10": {
|
| 91 |
+
"content": "<special_5>",
|
| 92 |
+
"lstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"rstrip": false,
|
| 95 |
+
"single_word": false,
|
| 96 |
+
"special": true
|
| 97 |
+
},
|
| 98 |
+
"11": {
|
| 99 |
+
"content": "<special_6>",
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"normalized": false,
|
| 102 |
+
"rstrip": false,
|
| 103 |
+
"single_word": false,
|
| 104 |
+
"special": true
|
| 105 |
+
},
|
| 106 |
+
"12": {
|
| 107 |
+
"content": "<special_7>",
|
| 108 |
+
"lstrip": false,
|
| 109 |
+
"normalized": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"single_word": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
"13": {
|
| 115 |
+
"content": "<special_8>",
|
| 116 |
+
"lstrip": false,
|
| 117 |
+
"normalized": false,
|
| 118 |
+
"rstrip": false,
|
| 119 |
+
"single_word": false,
|
| 120 |
+
"special": true
|
| 121 |
+
},
|
| 122 |
+
"14": {
|
| 123 |
+
"content": "<special_9>",
|
| 124 |
+
"lstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"single_word": false,
|
| 128 |
+
"special": true
|
| 129 |
+
},
|
| 130 |
+
"15": {
|
| 131 |
+
"content": "<special_10>",
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"normalized": false,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"special": true
|
| 137 |
+
}
|
| 138 |
+
},
|
| 139 |
+
"bos_token": "<s>",
|
| 140 |
+
"clean_up_tokenization_spaces": false,
|
| 141 |
+
"eos_token": "</s>",
|
| 142 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 143 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 144 |
+
"unk_token": "<unk>"
|
| 145 |
+
}
|