Text Generation
Transformers
Safetensors
PyTorch
ONNX
English
qtensorformer
q-tensorformer
high-throughput-inference
tensor-train
tensor-networks
tensorrt-llm
vllm
continuous-batching
paged-attention
speculative-decoding
zero-svd
adaptive-computation
dynamic-neural-networks
kv-cache
kv-cache-quantization
attention-sinks
lyapunov-stability
control-theory
contextual-bandits
edge-ai
edge-inference
on-device-ai
model-compression
hopper-h100
blackwell-b200
jetson-orin
jetson-thor
grouped-query-attention
rotary-position-embeddings
custom_code
academic-paper
ieee
neurips
vit-ap-university
deepseek
deepseek-r1
reasoning
chain-of-thought
gsm8k
openai-compatible
fastapi
rest-api
sse-streaming
onnx-runtime
embedded-ai
hardware-telemetry
power-efficiency
green-ai
raspberry-pi
smollm2
qwen2.5
llama-3.2
apple-silicon
File size: 4,993 Bytes
d279df0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 | {
"format": "QTensorFormerTokenizer",
"version": "1.0.0",
"vocab_size": 256,
"model_max_length": 64,
"special_tokens": {
"pad_token": "<pad>",
"pad_token_id": 0,
"bos_token": "<bos>",
"bos_token_id": 1,
"eos_token": "<eos>",
"eos_token_id": 2,
"unk_token": "<unk>",
"unk_token_id": 3
},
"vocab_sha256": "fc7ee274009d3aad8132b5f4de4c09091055439e22aa6b44196cab3ceb1db01e",
"vocab": {
"<pad>": 0,
"<bos>": 1,
"<eos>": 2,
"<unk>": 3,
"\t": 4,
"\n": 5,
"\r": 6,
" ": 7,
"!": 8,
"\"": 9,
"#": 10,
"$": 11,
"%": 12,
"&": 13,
"'": 14,
"(": 15,
")": 16,
"*": 17,
"+": 18,
",": 19,
"-": 20,
".": 21,
"/": 22,
"0": 23,
"1": 24,
"2": 25,
"3": 26,
"4": 27,
"5": 28,
"6": 29,
"7": 30,
"8": 31,
"9": 32,
":": 33,
";": 34,
"<": 35,
"=": 36,
">": 37,
"?": 38,
"@": 39,
"A": 40,
"B": 41,
"C": 42,
"D": 43,
"E": 44,
"F": 45,
"G": 46,
"H": 47,
"I": 48,
"J": 49,
"K": 50,
"L": 51,
"M": 52,
"N": 53,
"O": 54,
"P": 55,
"Q": 56,
"R": 57,
"S": 58,
"T": 59,
"U": 60,
"V": 61,
"W": 62,
"X": 63,
"Y": 64,
"Z": 65,
"[": 66,
"\\": 67,
"]": 68,
"^": 69,
"_": 70,
"`": 71,
"a": 72,
"b": 73,
"c": 74,
"d": 75,
"e": 76,
"f": 77,
"g": 78,
"h": 79,
"i": 80,
"j": 81,
"k": 82,
"l": 83,
"m": 84,
"n": 85,
"o": 86,
"p": 87,
"q": 88,
"r": 89,
"s": 90,
"t": 91,
"u": 92,
"v": 93,
"w": 94,
"x": 95,
"y": 96,
"z": 97,
"{": 98,
"|": 99,
"}": 100,
"~": 101,
" the": 102,
" and": 103,
" of": 104,
" or": 105,
" tokens": 106,
" in": 107,
" memory": 108,
" are": 109,
" attention": 110,
" by": 111,
" sequence": 112,
" to": 113,
" into": 114,
" models": 115,
"In": 116,
" KV-cache": 117,
" Tensor-Train": 118,
" across": 119,
" as": 120,
" can": 121,
" gates": 122,
" is": 123,
" key": 124,
" quantum": 125,
" state": 126,
" Transformer": 127,
" an": 128,
" between": 129,
" dimension": 130,
" during": 131,
" for": 132,
" from": 133,
" heads": 134,
" learning": 135,
" model": 136,
" networks": 137,
" on": 138,
" parameter": 139,
" rank": 140,
" requires": 141,
" rotations": 142,
" such": 143,
" these": 144,
" using": 145,
"By": 146,
"The": 147,
" GQA": 148,
" all": 149,
" allocation": 150,
" architectures": 151,
" be": 152,
" capacity": 153,
" classical": 154,
" compression": 155,
" cores": 156,
" dense": 157,
" directly": 158,
" dynamically": 159,
" execution": 160,
" footprint": 161,
" generation": 162,
" hardware": 163,
" head": 164,
" hidden": 165,
" high": 166,
" inference": 167,
" information": 168,
" input": 169,
" key-value": 170,
" keys": 171,
" language": 172,
" layer": 173,
" linear": 174,
" linearly": 175,
" machine": 176,
" multiple": 177,
" neural": 178,
" number": 179,
" operations": 180,
" perplexity": 181,
" position": 182,
" precision": 183,
" projecting": 184,
" projections": 185,
" queries": 186,
" query": 187,
" rather": 188,
" reducing": 189,
" representation": 190,
" resource": 191,
" scores": 192,
" standard": 193,
" states": 194,
" substantial": 195,
" tensor": 196,
" than": 197,
" this": 198,
" token": 199,
" value": 200,
" while": 201,
" with": 202,
"Attention": 203,
" ALU": 204,
" Bloch": 205,
" DRAM": 206,
" FFNs": 207,
" Hilbert": 208,
" Lie": 209,
" Meyer-Wallach": 210,
" RoPE": 211,
" Transformers": 212,
" according": 213,
" achieve": 214,
" adaptive": 215,
" adjacent": 216,
" adjusted": 217,
" aggregated": 218,
" allocator": 219,
" applies": 220,
" architecture": 221,
" articles": 222,
" artificial": 223,
" at": 224,
" attended": 225,
" autonomous": 226,
" autoregressive": 227,
" available": 228,
" back": 229,
" bandwidth": 230,
" before": 231,
" beginning": 232,
" benchmarks": 233,
" bus": 234,
" cache": 235,
" chain": 236,
" characterizes": 237,
" chattering": 238,
" circuits": 239,
" closed-loop": 240,
" combining": 241,
" common": 242,
" commonly": 243,
" complex": 244,
" compressing": 245,
" computational": 246,
" compute": 247,
" compute-bound": 248,
" computed": 249,
" concurrently": 250,
" constitute": 251,
" consume": 252,
" consumption": 253,
" contracted": 254,
" contrast": 255
}
} |