Update original/config.json
Browse files- original/config.json +13 -142
original/config.json
CHANGED
|
@@ -1,144 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 10 |
-
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
|
| 11 |
-
"AutoTokenizer": "Xenova/gpt-4o"
|
| 12 |
-
},
|
| 13 |
-
"bos_token_id": 199999,
|
| 14 |
-
"embd_pdrop": 0.0,
|
| 15 |
-
"eos_token_id": 199999,
|
| 16 |
-
"full_attn_mod": 1,
|
| 17 |
-
"hidden_act": "silu",
|
| 18 |
-
"hidden_size": 3072,
|
| 19 |
-
"initializer_range": 0.02,
|
| 20 |
-
"intermediate_size": 8192,
|
| 21 |
-
"interpolate_factor": 1,
|
| 22 |
-
"lm_head_bias": false,
|
| 23 |
-
"max_position_embeddings": 131072,
|
| 24 |
-
"mlp_bias": false,
|
| 25 |
-
"model_type": "phi3",
|
| 26 |
-
"num_attention_heads": 24,
|
| 27 |
-
"num_hidden_layers": 32,
|
| 28 |
-
"num_key_value_heads": 8,
|
| 29 |
-
"original_max_position_embeddings": 4096,
|
| 30 |
-
"pad_token_id": 199999,
|
| 31 |
-
"partial_rotary_factor": 0.75,
|
| 32 |
-
"resid_pdrop": 0.0,
|
| 33 |
-
"rms_norm_eps": 1e-05,
|
| 34 |
-
"rope_scaling": {
|
| 35 |
-
"long_factor": [
|
| 36 |
-
1,
|
| 37 |
-
1.118320672,
|
| 38 |
-
1.250641126,
|
| 39 |
-
1.398617824,
|
| 40 |
-
1.564103225,
|
| 41 |
-
1.74916897,
|
| 42 |
-
1.956131817,
|
| 43 |
-
2.187582649,
|
| 44 |
-
2.446418898,
|
| 45 |
-
2.735880826,
|
| 46 |
-
3.059592084,
|
| 47 |
-
3.421605075,
|
| 48 |
-
3.826451687,
|
| 49 |
-
4.279200023,
|
| 50 |
-
4.785517845,
|
| 51 |
-
5.351743533,
|
| 52 |
-
5.984965424,
|
| 53 |
-
6.693110555,
|
| 54 |
-
7.485043894,
|
| 55 |
-
8.370679318,
|
| 56 |
-
9.36110372,
|
| 57 |
-
10.4687158,
|
| 58 |
-
11.70738129,
|
| 59 |
-
13.09260651,
|
| 60 |
-
14.64173252,
|
| 61 |
-
16.37415215,
|
| 62 |
-
18.31155283,
|
| 63 |
-
20.47818807,
|
| 64 |
-
22.90118105,
|
| 65 |
-
25.61086418,
|
| 66 |
-
28.64115884,
|
| 67 |
-
32.03,
|
| 68 |
-
32.1,
|
| 69 |
-
32.13,
|
| 70 |
-
32.23,
|
| 71 |
-
32.6,
|
| 72 |
-
32.61,
|
| 73 |
-
32.64,
|
| 74 |
-
32.66,
|
| 75 |
-
32.7,
|
| 76 |
-
32.71,
|
| 77 |
-
32.93,
|
| 78 |
-
32.97,
|
| 79 |
-
33.28,
|
| 80 |
-
33.49,
|
| 81 |
-
33.5,
|
| 82 |
-
44.16,
|
| 83 |
-
47.77
|
| 84 |
-
],
|
| 85 |
-
"short_factor": [
|
| 86 |
-
1.0,
|
| 87 |
-
1.0,
|
| 88 |
-
1.0,
|
| 89 |
-
1.0,
|
| 90 |
-
1.0,
|
| 91 |
-
1.0,
|
| 92 |
-
1.0,
|
| 93 |
-
1.0,
|
| 94 |
-
1.0,
|
| 95 |
-
1.0,
|
| 96 |
-
1.0,
|
| 97 |
-
1.0,
|
| 98 |
-
1.0,
|
| 99 |
-
1.0,
|
| 100 |
-
1.0,
|
| 101 |
-
1.0,
|
| 102 |
-
1.0,
|
| 103 |
-
1.0,
|
| 104 |
-
1.0,
|
| 105 |
-
1.0,
|
| 106 |
-
1.0,
|
| 107 |
-
1.0,
|
| 108 |
-
1.0,
|
| 109 |
-
1.0,
|
| 110 |
-
1.0,
|
| 111 |
-
1.0,
|
| 112 |
-
1.0,
|
| 113 |
-
1.0,
|
| 114 |
-
1.0,
|
| 115 |
-
1.0,
|
| 116 |
-
1.0,
|
| 117 |
-
1.0,
|
| 118 |
-
1.0,
|
| 119 |
-
1.0,
|
| 120 |
-
1.0,
|
| 121 |
-
1.0,
|
| 122 |
-
1.0,
|
| 123 |
-
1.0,
|
| 124 |
-
1.0,
|
| 125 |
-
1.0,
|
| 126 |
-
1.0,
|
| 127 |
-
1.0,
|
| 128 |
-
1.0,
|
| 129 |
-
1.0,
|
| 130 |
-
1.0,
|
| 131 |
-
1.0,
|
| 132 |
-
1.0,
|
| 133 |
-
1.0
|
| 134 |
-
],
|
| 135 |
-
"type": "longrope"
|
| 136 |
-
},
|
| 137 |
"rope_theta": 10000.0,
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
|
| 144 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"dim": 3072,
|
| 3 |
+
"ffn_dim_multiplier": 1,
|
| 4 |
+
"hidden_dim": 8192,
|
| 5 |
+
"n_heads": 24,
|
| 6 |
+
"n_kv_heads": 8,
|
| 7 |
+
"n_layers": 32,
|
| 8 |
+
"norm_eps": 1e-05,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"rope_theta": 10000.0,
|
| 10 |
+
"use_scaled_rope": false,
|
| 11 |
+
"vocab_size": 200064,
|
| 12 |
+
"use_hf_rope": true,
|
| 13 |
+
"partial_rotary_factor": 0.75,
|
| 14 |
+
"attention_qkv_bias": false
|
| 15 |
+
}
|
|
|