Upload config.json with huggingface_hub
Browse files- config.json +151 -0
config.json
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Phi3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
|
| 10 |
+
"AutoTokenizer": "Xenova/gpt-4o"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 199999,
|
| 13 |
+
"embd_pdrop": 0.0,
|
| 14 |
+
"eos_token_id": 199999,
|
| 15 |
+
"full_attn_mod": 1,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 3072,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 8192,
|
| 20 |
+
"interpolate_factor": 1,
|
| 21 |
+
"lm_head_bias": false,
|
| 22 |
+
"max_position_embeddings": 131072,
|
| 23 |
+
"mlp_bias": false,
|
| 24 |
+
"model_type": "phi3",
|
| 25 |
+
"num_attention_heads": 24,
|
| 26 |
+
"num_hidden_layers": 32,
|
| 27 |
+
"num_key_value_heads": 8,
|
| 28 |
+
"original_max_position_embeddings": 4096,
|
| 29 |
+
"pad_token_id": 199999,
|
| 30 |
+
"partial_rotary_factor": 0.75,
|
| 31 |
+
"quantization": {
|
| 32 |
+
"group_size": 64,
|
| 33 |
+
"bits": 4
|
| 34 |
+
},
|
| 35 |
+
"quantization_config": {
|
| 36 |
+
"group_size": 64,
|
| 37 |
+
"bits": 4
|
| 38 |
+
},
|
| 39 |
+
"resid_pdrop": 0.0,
|
| 40 |
+
"rms_norm_eps": 1e-05,
|
| 41 |
+
"rope_scaling": {
|
| 42 |
+
"long_factor": [
|
| 43 |
+
1,
|
| 44 |
+
1.118320672,
|
| 45 |
+
1.250641126,
|
| 46 |
+
1.398617824,
|
| 47 |
+
1.564103225,
|
| 48 |
+
1.74916897,
|
| 49 |
+
1.956131817,
|
| 50 |
+
2.187582649,
|
| 51 |
+
2.446418898,
|
| 52 |
+
2.735880826,
|
| 53 |
+
3.059592084,
|
| 54 |
+
3.421605075,
|
| 55 |
+
3.826451687,
|
| 56 |
+
4.279200023,
|
| 57 |
+
4.785517845,
|
| 58 |
+
5.351743533,
|
| 59 |
+
5.984965424,
|
| 60 |
+
6.693110555,
|
| 61 |
+
7.485043894,
|
| 62 |
+
8.370679318,
|
| 63 |
+
9.36110372,
|
| 64 |
+
10.4687158,
|
| 65 |
+
11.70738129,
|
| 66 |
+
13.09260651,
|
| 67 |
+
14.64173252,
|
| 68 |
+
16.37415215,
|
| 69 |
+
18.31155283,
|
| 70 |
+
20.47818807,
|
| 71 |
+
22.90118105,
|
| 72 |
+
25.61086418,
|
| 73 |
+
28.64115884,
|
| 74 |
+
32.03,
|
| 75 |
+
32.1,
|
| 76 |
+
32.13,
|
| 77 |
+
32.23,
|
| 78 |
+
32.6,
|
| 79 |
+
32.61,
|
| 80 |
+
32.64,
|
| 81 |
+
32.66,
|
| 82 |
+
32.7,
|
| 83 |
+
32.71,
|
| 84 |
+
32.93,
|
| 85 |
+
32.97,
|
| 86 |
+
33.28,
|
| 87 |
+
33.49,
|
| 88 |
+
33.5,
|
| 89 |
+
44.16,
|
| 90 |
+
47.77
|
| 91 |
+
],
|
| 92 |
+
"short_factor": [
|
| 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 |
+
1.0,
|
| 135 |
+
1.0,
|
| 136 |
+
1.0,
|
| 137 |
+
1.0,
|
| 138 |
+
1.0,
|
| 139 |
+
1.0,
|
| 140 |
+
1.0
|
| 141 |
+
],
|
| 142 |
+
"type": "longrope"
|
| 143 |
+
},
|
| 144 |
+
"rope_theta": 10000.0,
|
| 145 |
+
"sliding_window": 262144,
|
| 146 |
+
"tie_word_embeddings": true,
|
| 147 |
+
"torch_dtype": "bfloat16",
|
| 148 |
+
"transformers_version": "4.45.0",
|
| 149 |
+
"use_cache": true,
|
| 150 |
+
"vocab_size": 200064
|
| 151 |
+
}
|