Upload folder using huggingface_hub
Browse files- config.json +164 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "False_Correct:NA",
|
| 14 |
+
"1": "False_Misconception:Adding_across",
|
| 15 |
+
"2": "False_Misconception:Adding_terms",
|
| 16 |
+
"3": "False_Misconception:Additive",
|
| 17 |
+
"4": "False_Misconception:Base_rate",
|
| 18 |
+
"5": "False_Misconception:Certainty",
|
| 19 |
+
"6": "False_Misconception:Definition",
|
| 20 |
+
"7": "False_Misconception:Denominator-only_change",
|
| 21 |
+
"8": "False_Misconception:Division",
|
| 22 |
+
"9": "False_Misconception:Duplication",
|
| 23 |
+
"10": "False_Misconception:Firstterm",
|
| 24 |
+
"11": "False_Misconception:FlipChange",
|
| 25 |
+
"12": "False_Misconception:Ignores_zeroes",
|
| 26 |
+
"13": "False_Misconception:Incomplete",
|
| 27 |
+
"14": "False_Misconception:Incorrect_equivalent_fraction_addition",
|
| 28 |
+
"15": "False_Misconception:Interior",
|
| 29 |
+
"16": "False_Misconception:Inverse_operation",
|
| 30 |
+
"17": "False_Misconception:Inversion",
|
| 31 |
+
"18": "False_Misconception:Irrelevant",
|
| 32 |
+
"19": "False_Misconception:Longer_is_bigger",
|
| 33 |
+
"20": "False_Misconception:Mult",
|
| 34 |
+
"21": "False_Misconception:Multiplying_by_4",
|
| 35 |
+
"22": "False_Misconception:Not_variable",
|
| 36 |
+
"23": "False_Misconception:Positive",
|
| 37 |
+
"24": "False_Misconception:Scale",
|
| 38 |
+
"25": "False_Misconception:Shorter_is_bigger",
|
| 39 |
+
"26": "False_Misconception:Subtraction",
|
| 40 |
+
"27": "False_Misconception:SwapDividend",
|
| 41 |
+
"28": "False_Misconception:Tacking",
|
| 42 |
+
"29": "False_Misconception:Unknowable",
|
| 43 |
+
"30": "False_Misconception:WNB",
|
| 44 |
+
"31": "False_Misconception:Whole_numbers_larger",
|
| 45 |
+
"32": "False_Misconception:Wrong_Fraction",
|
| 46 |
+
"33": "False_Misconception:Wrong_Operation",
|
| 47 |
+
"34": "False_Misconception:Wrong_fraction",
|
| 48 |
+
"35": "False_Misconception:Wrong_term",
|
| 49 |
+
"36": "False_Neither:NA",
|
| 50 |
+
"37": "True_Correct:NA",
|
| 51 |
+
"38": "True_Misconception:Adding_across",
|
| 52 |
+
"39": "True_Misconception:Additive",
|
| 53 |
+
"40": "True_Misconception:Base_rate",
|
| 54 |
+
"41": "True_Misconception:Definition",
|
| 55 |
+
"42": "True_Misconception:Denominator-only_change",
|
| 56 |
+
"43": "True_Misconception:Division",
|
| 57 |
+
"44": "True_Misconception:Duplication",
|
| 58 |
+
"45": "True_Misconception:Firstterm",
|
| 59 |
+
"46": "True_Misconception:FlipChange",
|
| 60 |
+
"47": "True_Misconception:Incomplete",
|
| 61 |
+
"48": "True_Misconception:Incorrect_equivalent_fraction_addition",
|
| 62 |
+
"49": "True_Misconception:Inversion",
|
| 63 |
+
"50": "True_Misconception:Irrelevant",
|
| 64 |
+
"51": "True_Misconception:Longer_is_bigger",
|
| 65 |
+
"52": "True_Misconception:Mult",
|
| 66 |
+
"53": "True_Misconception:Multiplying_by_4",
|
| 67 |
+
"54": "True_Misconception:Not_variable",
|
| 68 |
+
"55": "True_Misconception:Positive",
|
| 69 |
+
"56": "True_Misconception:Shorter_is_bigger",
|
| 70 |
+
"57": "True_Misconception:Subtraction",
|
| 71 |
+
"58": "True_Misconception:SwapDividend",
|
| 72 |
+
"59": "True_Misconception:Tacking",
|
| 73 |
+
"60": "True_Misconception:WNB",
|
| 74 |
+
"61": "True_Misconception:Whole_numbers_larger",
|
| 75 |
+
"62": "True_Misconception:Wrong_fraction",
|
| 76 |
+
"63": "True_Misconception:Wrong_term",
|
| 77 |
+
"64": "True_Neither:NA"
|
| 78 |
+
},
|
| 79 |
+
"initializer_range": 0.02,
|
| 80 |
+
"intermediate_size": 5632,
|
| 81 |
+
"label2id": {
|
| 82 |
+
"False_Correct:NA": 0,
|
| 83 |
+
"False_Misconception:Adding_across": 1,
|
| 84 |
+
"False_Misconception:Adding_terms": 2,
|
| 85 |
+
"False_Misconception:Additive": 3,
|
| 86 |
+
"False_Misconception:Base_rate": 4,
|
| 87 |
+
"False_Misconception:Certainty": 5,
|
| 88 |
+
"False_Misconception:Definition": 6,
|
| 89 |
+
"False_Misconception:Denominator-only_change": 7,
|
| 90 |
+
"False_Misconception:Division": 8,
|
| 91 |
+
"False_Misconception:Duplication": 9,
|
| 92 |
+
"False_Misconception:Firstterm": 10,
|
| 93 |
+
"False_Misconception:FlipChange": 11,
|
| 94 |
+
"False_Misconception:Ignores_zeroes": 12,
|
| 95 |
+
"False_Misconception:Incomplete": 13,
|
| 96 |
+
"False_Misconception:Incorrect_equivalent_fraction_addition": 14,
|
| 97 |
+
"False_Misconception:Interior": 15,
|
| 98 |
+
"False_Misconception:Inverse_operation": 16,
|
| 99 |
+
"False_Misconception:Inversion": 17,
|
| 100 |
+
"False_Misconception:Irrelevant": 18,
|
| 101 |
+
"False_Misconception:Longer_is_bigger": 19,
|
| 102 |
+
"False_Misconception:Mult": 20,
|
| 103 |
+
"False_Misconception:Multiplying_by_4": 21,
|
| 104 |
+
"False_Misconception:Not_variable": 22,
|
| 105 |
+
"False_Misconception:Positive": 23,
|
| 106 |
+
"False_Misconception:Scale": 24,
|
| 107 |
+
"False_Misconception:Shorter_is_bigger": 25,
|
| 108 |
+
"False_Misconception:Subtraction": 26,
|
| 109 |
+
"False_Misconception:SwapDividend": 27,
|
| 110 |
+
"False_Misconception:Tacking": 28,
|
| 111 |
+
"False_Misconception:Unknowable": 29,
|
| 112 |
+
"False_Misconception:WNB": 30,
|
| 113 |
+
"False_Misconception:Whole_numbers_larger": 31,
|
| 114 |
+
"False_Misconception:Wrong_Fraction": 32,
|
| 115 |
+
"False_Misconception:Wrong_Operation": 33,
|
| 116 |
+
"False_Misconception:Wrong_fraction": 34,
|
| 117 |
+
"False_Misconception:Wrong_term": 35,
|
| 118 |
+
"False_Neither:NA": 36,
|
| 119 |
+
"True_Correct:NA": 37,
|
| 120 |
+
"True_Misconception:Adding_across": 38,
|
| 121 |
+
"True_Misconception:Additive": 39,
|
| 122 |
+
"True_Misconception:Base_rate": 40,
|
| 123 |
+
"True_Misconception:Definition": 41,
|
| 124 |
+
"True_Misconception:Denominator-only_change": 42,
|
| 125 |
+
"True_Misconception:Division": 43,
|
| 126 |
+
"True_Misconception:Duplication": 44,
|
| 127 |
+
"True_Misconception:Firstterm": 45,
|
| 128 |
+
"True_Misconception:FlipChange": 46,
|
| 129 |
+
"True_Misconception:Incomplete": 47,
|
| 130 |
+
"True_Misconception:Incorrect_equivalent_fraction_addition": 48,
|
| 131 |
+
"True_Misconception:Inversion": 49,
|
| 132 |
+
"True_Misconception:Irrelevant": 50,
|
| 133 |
+
"True_Misconception:Longer_is_bigger": 51,
|
| 134 |
+
"True_Misconception:Mult": 52,
|
| 135 |
+
"True_Misconception:Multiplying_by_4": 53,
|
| 136 |
+
"True_Misconception:Not_variable": 54,
|
| 137 |
+
"True_Misconception:Positive": 55,
|
| 138 |
+
"True_Misconception:Shorter_is_bigger": 56,
|
| 139 |
+
"True_Misconception:Subtraction": 57,
|
| 140 |
+
"True_Misconception:SwapDividend": 58,
|
| 141 |
+
"True_Misconception:Tacking": 59,
|
| 142 |
+
"True_Misconception:WNB": 60,
|
| 143 |
+
"True_Misconception:Whole_numbers_larger": 61,
|
| 144 |
+
"True_Misconception:Wrong_fraction": 62,
|
| 145 |
+
"True_Misconception:Wrong_term": 63,
|
| 146 |
+
"True_Neither:NA": 64
|
| 147 |
+
},
|
| 148 |
+
"max_position_embeddings": 2048,
|
| 149 |
+
"mlp_bias": false,
|
| 150 |
+
"model_type": "llama",
|
| 151 |
+
"num_attention_heads": 32,
|
| 152 |
+
"num_hidden_layers": 22,
|
| 153 |
+
"num_key_value_heads": 4,
|
| 154 |
+
"pad_token_id": 2,
|
| 155 |
+
"pretraining_tp": 1,
|
| 156 |
+
"rms_norm_eps": 1e-05,
|
| 157 |
+
"rope_scaling": null,
|
| 158 |
+
"rope_theta": 10000.0,
|
| 159 |
+
"tie_word_embeddings": false,
|
| 160 |
+
"torch_dtype": "bfloat16",
|
| 161 |
+
"transformers_version": "4.54.0",
|
| 162 |
+
"use_cache": true,
|
| 163 |
+
"vocab_size": 32000
|
| 164 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feaf33156b882feca4c6620f598417ed1929846c888fe45df4e4ad329dcda3db
|
| 3 |
+
size 2069314072
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"extra_special_tokens": {},
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "left",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e4373051f9e0648a96f4e9d730771291ce4486b6b562e12cafc9c50948c977c
|
| 3 |
+
size 5304
|