chipformer / config.json
divagr1925's picture
chipformer v0.1.0
4eec64a verified
Raw History Blame Contribute Delete
5.11 kB
{
"architectures": [
"ChipformerForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_chipformer.ChipformerConfig",
"AutoModelForCausalLM": "modeling_chipformer.ChipformerForCausalLM"
},
"model_type": "chipformer",
"d_model": 382,
"vocab_size": 8708,
"beta": 1000.0,
"layers": [
{
"heads": [
[
2,
2
],
[
2,
1
],
[
2,
2
]
],
"ffn_units": 2,
"head_names": [
"write_addr",
"rec_start",
"last_tick"
]
},
{
"heads": [
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
2
],
[
2,
3
],
[
2,
2
]
],
"ffn_units": 91,
"head_names": [
"PC",
"I",
"SP",
"DT",
"ST",
"RNG",
"V0",
"key0",
"key1",
"key2",
"key3",
"key4",
"key5",
"key6",
"key7",
"key8",
"key9",
"keyA",
"keyB",
"keyC",
"keyD",
"keyE",
"keyF",
"q.shift",
"q.loadstore",
"q.clip",
"q.logic",
"q.jump",
"q.vforder",
"old",
"old.cls"
]
},
{
"heads": [
[
2,
2
]
],
"ffn_units": 16477,
"head_names": [
"op_hi"
]
},
{
"heads": [
[
2,
2
],
[
2,
2
]
],
"ffn_units": 1054,
"head_names": [
"op_lo",
"stack_top"
]
},
{
"heads": [
[
2,
2
]
],
"ffn_units": 1108,
"head_names": [
"VX"
]
},
{
"heads": [
[
2,
2
]
],
"ffn_units": 1117,
"head_names": [
"VY"
]
},
{
"heads": [],
"ffn_units": 1080,
"head_names": []
},
{
"heads": [],
"ffn_units": 65,
"head_names": []
},
{
"heads": [],
"ffn_units": 52,
"head_names": []
},
{
"heads": [
[
2,
26
]
],
"ffn_units": 88,
"head_names": [
"ctx"
]
},
{
"heads": [],
"ffn_units": 31,
"head_names": []
},
{
"heads": [
[
2,
2
]
],
"ffn_units": 4,
"head_names": [
"vread"
]
},
{
"heads": [],
"ffn_units": 1007,
"head_names": []
},
{
"heads": [],
"ffn_units": 64,
"head_names": []
},
{
"heads": [],
"ffn_units": 8,
"head_names": []
},
{
"heads": [],
"ffn_units": 2,
"head_names": []
},
{
"heads": [
[
2,
2
]
],
"ffn_units": 2,
"head_names": [
"last_collision"
]
},
{
"heads": [],
"ffn_units": 24,
"head_names": []
}
],
"machine": {
"VAL_BASE": 0,
"ADDR_BASE": 4096,
"STEP": 8705,
"TICK": 8706,
"BOOT": 8707,
"NUM_CELLS": 4609,
"NULL": 4608,
"CLS": 4118,
"PC": 4113,
"RNG": 4117,
"KEYS": 4144,
"DISPLAY": 4352,
"DISPLAY_W": 64,
"DISPLAY_H": 32,
"PROGRAM_START": 512,
"FONT_BASE": 80,
"RNG_SEED": 2766,
"QUIRKS": 4119,
"FONT": [
240,
144,
144,
144,
240,
32,
96,
32,
32,
112,
240,
16,
240,
128,
240,
240,
16,
240,
16,
240,
144,
144,
240,
16,
16,
240,
128,
240,
16,
240,
240,
128,
240,
144,
240,
240,
16,
32,
64,
64,
240,
144,
240,
144,
240,
240,
144,
240,
16,
240,
240,
144,
240,
144,
144,
224,
144,
224,
144,
224,
240,
128,
128,
128,
240,
224,
144,
144,
144,
224,
240,
128,
240,
128,
240,
240,
128,
240,
128,
128
],
"QUIRK_NAMES": [
"shift",
"loadstore",
"clip",
"logic",
"jump",
"vforder"
],
"PROFILES": {
"octo": [],
"chip48": [
"shift",
"loadstore",
"clip"
],
"cosmac": [
"logic",
"clip"
]
}
},
"max_position": 4194304,
"rollover_at": 250000,
"params": 32328660,
"nonzero_params": 139229,
"dtype": "float64",
"torch_dtype": "float64",
"tie_word_embeddings": false
}