Upload folder using huggingface_hub
Browse files- checkpoint-80905/config.json +35 -0
- checkpoint-80905/generation_config.json +6 -0
- checkpoint-80905/model.safetensors +3 -0
- checkpoint-80905/optimizer.pt +3 -0
- checkpoint-80905/rng_state.pth +3 -0
- checkpoint-80905/scheduler.pt +3 -0
- checkpoint-80905/special_tokens_map.json +5 -0
- checkpoint-80905/tokenizer.json +269 -0
- checkpoint-80905/tokenizer_config.json +18 -0
- checkpoint-80905/trainer_state.json +0 -0
- checkpoint-80905/training_args.bin +3 -0
checkpoint-80905/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"allow_neg_eigval": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GatedDeltaNetForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attn": null,
|
| 7 |
+
"attn_mode": "chunk",
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"conv_size": 4,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"expand_v": 2.0,
|
| 12 |
+
"fuse_cross_entropy": true,
|
| 13 |
+
"fuse_norm": true,
|
| 14 |
+
"fuse_swiglu": true,
|
| 15 |
+
"head_dim": 256,
|
| 16 |
+
"hidden_act": "swish",
|
| 17 |
+
"hidden_ratio": 4,
|
| 18 |
+
"hidden_size": 256,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": null,
|
| 21 |
+
"max_position_embeddings": 2048,
|
| 22 |
+
"model_type": "gated_deltanet",
|
| 23 |
+
"norm_eps": 1e-06,
|
| 24 |
+
"num_heads": 8,
|
| 25 |
+
"num_hidden_layers": 4,
|
| 26 |
+
"num_v_heads": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.45.0",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"use_gate": true,
|
| 32 |
+
"use_l2warp": false,
|
| 33 |
+
"use_short_conv": true,
|
| 34 |
+
"vocab_size": 241
|
| 35 |
+
}
|
checkpoint-80905/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.45.0"
|
| 6 |
+
}
|
checkpoint-80905/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bc1a6c33ea29abca1e3f8af012e04dbc03a57af4dd301287cbd5aadf52fb599
|
| 3 |
+
size 77654816
|
checkpoint-80905/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a543bb0f792bb0e7d2243c7e8c8427dd92b6ab2d8106050218b2e20507fbd55
|
| 3 |
+
size 155357050
|
checkpoint-80905/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d4b7fd4228865f5c7b65538fc3222d5008d5fd8ec426ab2a97a6055b372c21b
|
| 3 |
+
size 14244
|
checkpoint-80905/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fae7cfca15e5fec85cecea5066b52490acd374cc08b56812514f4160a8a05d4
|
| 3 |
+
size 1064
|
checkpoint-80905/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<pad>",
|
| 3 |
+
"eos_token": "<pad>",
|
| 4 |
+
"pad_token": "<pad>"
|
| 5 |
+
}
|
checkpoint-80905/tokenizer.json
ADDED
|
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<pad>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
}
|
| 15 |
+
],
|
| 16 |
+
"normalizer": null,
|
| 17 |
+
"pre_tokenizer": {
|
| 18 |
+
"type": "WhitespaceSplit"
|
| 19 |
+
},
|
| 20 |
+
"post_processor": null,
|
| 21 |
+
"decoder": null,
|
| 22 |
+
"model": {
|
| 23 |
+
"type": "WordLevel",
|
| 24 |
+
"vocab": {
|
| 25 |
+
"<pad>": 0,
|
| 26 |
+
" 12345": 1,
|
| 27 |
+
" 12354": 2,
|
| 28 |
+
" 12435": 3,
|
| 29 |
+
" 12453": 4,
|
| 30 |
+
" 12534": 5,
|
| 31 |
+
" 12543": 6,
|
| 32 |
+
" 13245": 7,
|
| 33 |
+
" 13254": 8,
|
| 34 |
+
" 13425": 9,
|
| 35 |
+
" 13452": 10,
|
| 36 |
+
" 13524": 11,
|
| 37 |
+
" 13542": 12,
|
| 38 |
+
" 14235": 13,
|
| 39 |
+
" 14253": 14,
|
| 40 |
+
" 14325": 15,
|
| 41 |
+
" 14352": 16,
|
| 42 |
+
" 14523": 17,
|
| 43 |
+
" 14532": 18,
|
| 44 |
+
" 15234": 19,
|
| 45 |
+
" 15243": 20,
|
| 46 |
+
" 15324": 21,
|
| 47 |
+
" 15342": 22,
|
| 48 |
+
" 15423": 23,
|
| 49 |
+
" 15432": 24,
|
| 50 |
+
" 21345": 25,
|
| 51 |
+
" 21354": 26,
|
| 52 |
+
" 21435": 27,
|
| 53 |
+
" 21453": 28,
|
| 54 |
+
" 21534": 29,
|
| 55 |
+
" 21543": 30,
|
| 56 |
+
" 23145": 31,
|
| 57 |
+
" 23154": 32,
|
| 58 |
+
" 23415": 33,
|
| 59 |
+
" 23451": 34,
|
| 60 |
+
" 23514": 35,
|
| 61 |
+
" 23541": 36,
|
| 62 |
+
" 24135": 37,
|
| 63 |
+
" 24153": 38,
|
| 64 |
+
" 24315": 39,
|
| 65 |
+
" 24351": 40,
|
| 66 |
+
" 24513": 41,
|
| 67 |
+
" 24531": 42,
|
| 68 |
+
" 25134": 43,
|
| 69 |
+
" 25143": 44,
|
| 70 |
+
" 25314": 45,
|
| 71 |
+
" 25341": 46,
|
| 72 |
+
" 25413": 47,
|
| 73 |
+
" 25431": 48,
|
| 74 |
+
" 31245": 49,
|
| 75 |
+
" 31254": 50,
|
| 76 |
+
" 31425": 51,
|
| 77 |
+
" 31452": 52,
|
| 78 |
+
" 31524": 53,
|
| 79 |
+
" 31542": 54,
|
| 80 |
+
" 32145": 55,
|
| 81 |
+
" 32154": 56,
|
| 82 |
+
" 32415": 57,
|
| 83 |
+
" 32451": 58,
|
| 84 |
+
" 32514": 59,
|
| 85 |
+
" 32541": 60,
|
| 86 |
+
" 34125": 61,
|
| 87 |
+
" 34152": 62,
|
| 88 |
+
" 34215": 63,
|
| 89 |
+
" 34251": 64,
|
| 90 |
+
" 34512": 65,
|
| 91 |
+
" 34521": 66,
|
| 92 |
+
" 35124": 67,
|
| 93 |
+
" 35142": 68,
|
| 94 |
+
" 35214": 69,
|
| 95 |
+
" 35241": 70,
|
| 96 |
+
" 35412": 71,
|
| 97 |
+
" 35421": 72,
|
| 98 |
+
" 41235": 73,
|
| 99 |
+
" 41253": 74,
|
| 100 |
+
" 41325": 75,
|
| 101 |
+
" 41352": 76,
|
| 102 |
+
" 41523": 77,
|
| 103 |
+
" 41532": 78,
|
| 104 |
+
" 42135": 79,
|
| 105 |
+
" 42153": 80,
|
| 106 |
+
" 42315": 81,
|
| 107 |
+
" 42351": 82,
|
| 108 |
+
" 42513": 83,
|
| 109 |
+
" 42531": 84,
|
| 110 |
+
" 43125": 85,
|
| 111 |
+
" 43152": 86,
|
| 112 |
+
" 43215": 87,
|
| 113 |
+
" 43251": 88,
|
| 114 |
+
" 43512": 89,
|
| 115 |
+
" 43521": 90,
|
| 116 |
+
" 45123": 91,
|
| 117 |
+
" 45132": 92,
|
| 118 |
+
" 45213": 93,
|
| 119 |
+
" 45231": 94,
|
| 120 |
+
" 45312": 95,
|
| 121 |
+
" 45321": 96,
|
| 122 |
+
" 51234": 97,
|
| 123 |
+
" 51243": 98,
|
| 124 |
+
" 51324": 99,
|
| 125 |
+
" 51342": 100,
|
| 126 |
+
" 51423": 101,
|
| 127 |
+
" 51432": 102,
|
| 128 |
+
" 52134": 103,
|
| 129 |
+
" 52143": 104,
|
| 130 |
+
" 52314": 105,
|
| 131 |
+
" 52341": 106,
|
| 132 |
+
" 52413": 107,
|
| 133 |
+
" 52431": 108,
|
| 134 |
+
" 53124": 109,
|
| 135 |
+
" 53142": 110,
|
| 136 |
+
" 53214": 111,
|
| 137 |
+
" 53241": 112,
|
| 138 |
+
" 53412": 113,
|
| 139 |
+
" 53421": 114,
|
| 140 |
+
" 54123": 115,
|
| 141 |
+
" 54132": 116,
|
| 142 |
+
" 54213": 117,
|
| 143 |
+
" 54231": 118,
|
| 144 |
+
" 54312": 119,
|
| 145 |
+
" 54321": 120,
|
| 146 |
+
"12345": 121,
|
| 147 |
+
"12354": 122,
|
| 148 |
+
"12435": 123,
|
| 149 |
+
"12453": 124,
|
| 150 |
+
"12534": 125,
|
| 151 |
+
"12543": 126,
|
| 152 |
+
"13245": 127,
|
| 153 |
+
"13254": 128,
|
| 154 |
+
"13425": 129,
|
| 155 |
+
"13452": 130,
|
| 156 |
+
"13524": 131,
|
| 157 |
+
"13542": 132,
|
| 158 |
+
"14235": 133,
|
| 159 |
+
"14253": 134,
|
| 160 |
+
"14325": 135,
|
| 161 |
+
"14352": 136,
|
| 162 |
+
"14523": 137,
|
| 163 |
+
"14532": 138,
|
| 164 |
+
"15234": 139,
|
| 165 |
+
"15243": 140,
|
| 166 |
+
"15324": 141,
|
| 167 |
+
"15342": 142,
|
| 168 |
+
"15423": 143,
|
| 169 |
+
"15432": 144,
|
| 170 |
+
"21345": 145,
|
| 171 |
+
"21354": 146,
|
| 172 |
+
"21435": 147,
|
| 173 |
+
"21453": 148,
|
| 174 |
+
"21534": 149,
|
| 175 |
+
"21543": 150,
|
| 176 |
+
"23145": 151,
|
| 177 |
+
"23154": 152,
|
| 178 |
+
"23415": 153,
|
| 179 |
+
"23451": 154,
|
| 180 |
+
"23514": 155,
|
| 181 |
+
"23541": 156,
|
| 182 |
+
"24135": 157,
|
| 183 |
+
"24153": 158,
|
| 184 |
+
"24315": 159,
|
| 185 |
+
"24351": 160,
|
| 186 |
+
"24513": 161,
|
| 187 |
+
"24531": 162,
|
| 188 |
+
"25134": 163,
|
| 189 |
+
"25143": 164,
|
| 190 |
+
"25314": 165,
|
| 191 |
+
"25341": 166,
|
| 192 |
+
"25413": 167,
|
| 193 |
+
"25431": 168,
|
| 194 |
+
"31245": 169,
|
| 195 |
+
"31254": 170,
|
| 196 |
+
"31425": 171,
|
| 197 |
+
"31452": 172,
|
| 198 |
+
"31524": 173,
|
| 199 |
+
"31542": 174,
|
| 200 |
+
"32145": 175,
|
| 201 |
+
"32154": 176,
|
| 202 |
+
"32415": 177,
|
| 203 |
+
"32451": 178,
|
| 204 |
+
"32514": 179,
|
| 205 |
+
"32541": 180,
|
| 206 |
+
"34125": 181,
|
| 207 |
+
"34152": 182,
|
| 208 |
+
"34215": 183,
|
| 209 |
+
"34251": 184,
|
| 210 |
+
"34512": 185,
|
| 211 |
+
"34521": 186,
|
| 212 |
+
"35124": 187,
|
| 213 |
+
"35142": 188,
|
| 214 |
+
"35214": 189,
|
| 215 |
+
"35241": 190,
|
| 216 |
+
"35412": 191,
|
| 217 |
+
"35421": 192,
|
| 218 |
+
"41235": 193,
|
| 219 |
+
"41253": 194,
|
| 220 |
+
"41325": 195,
|
| 221 |
+
"41352": 196,
|
| 222 |
+
"41523": 197,
|
| 223 |
+
"41532": 198,
|
| 224 |
+
"42135": 199,
|
| 225 |
+
"42153": 200,
|
| 226 |
+
"42315": 201,
|
| 227 |
+
"42351": 202,
|
| 228 |
+
"42513": 203,
|
| 229 |
+
"42531": 204,
|
| 230 |
+
"43125": 205,
|
| 231 |
+
"43152": 206,
|
| 232 |
+
"43215": 207,
|
| 233 |
+
"43251": 208,
|
| 234 |
+
"43512": 209,
|
| 235 |
+
"43521": 210,
|
| 236 |
+
"45123": 211,
|
| 237 |
+
"45132": 212,
|
| 238 |
+
"45213": 213,
|
| 239 |
+
"45231": 214,
|
| 240 |
+
"45312": 215,
|
| 241 |
+
"45321": 216,
|
| 242 |
+
"51234": 217,
|
| 243 |
+
"51243": 218,
|
| 244 |
+
"51324": 219,
|
| 245 |
+
"51342": 220,
|
| 246 |
+
"51423": 221,
|
| 247 |
+
"51432": 222,
|
| 248 |
+
"52134": 223,
|
| 249 |
+
"52143": 224,
|
| 250 |
+
"52314": 225,
|
| 251 |
+
"52341": 226,
|
| 252 |
+
"52413": 227,
|
| 253 |
+
"52431": 228,
|
| 254 |
+
"53124": 229,
|
| 255 |
+
"53142": 230,
|
| 256 |
+
"53214": 231,
|
| 257 |
+
"53241": 232,
|
| 258 |
+
"53412": 233,
|
| 259 |
+
"53421": 234,
|
| 260 |
+
"54123": 235,
|
| 261 |
+
"54132": 236,
|
| 262 |
+
"54213": 237,
|
| 263 |
+
"54231": 238,
|
| 264 |
+
"54312": 239,
|
| 265 |
+
"54321": 240
|
| 266 |
+
},
|
| 267 |
+
"unk_token": "<pad>"
|
| 268 |
+
}
|
| 269 |
+
}
|
checkpoint-80905/tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
}
|
| 11 |
+
},
|
| 12 |
+
"bos_token": "<pad>",
|
| 13 |
+
"clean_up_tokenization_spaces": true,
|
| 14 |
+
"eos_token": "<pad>",
|
| 15 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 18 |
+
}
|
checkpoint-80905/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-80905/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97e63651324affd7976365e3306b6dcdda9ae9b520a22f33cd9d72b4aa9c39e4
|
| 3 |
+
size 5176
|