Upload config.json with huggingface_hub
Browse files- config.json +143 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,143 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "architectures": [
         | 
| 3 | 
            +
                "Phi3ForCausalLM"
         | 
| 4 | 
            +
              ],
         | 
| 5 | 
            +
              "attention_bias": false,
         | 
| 6 | 
            +
              "attention_dropout": 0.0,
         | 
| 7 | 
            +
              "auto_map": {
         | 
| 8 | 
            +
                "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
         | 
| 9 | 
            +
                "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
         | 
| 10 | 
            +
                "AutoTokenizer": "microsoft/Phi-4-mini-instruct--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": 4096,
         | 
| 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 | 
            +
              "resid_pdrop": 0.0,
         | 
| 32 | 
            +
              "rms_norm_eps": 1e-05,
         | 
| 33 | 
            +
              "rope_scaling": {
         | 
| 34 | 
            +
                "long_factor": [
         | 
| 35 | 
            +
                  1,
         | 
| 36 | 
            +
                  1.118320672,
         | 
| 37 | 
            +
                  1.250641126,
         | 
| 38 | 
            +
                  1.398617824,
         | 
| 39 | 
            +
                  1.564103225,
         | 
| 40 | 
            +
                  1.74916897,
         | 
| 41 | 
            +
                  1.956131817,
         | 
| 42 | 
            +
                  2.187582649,
         | 
| 43 | 
            +
                  2.446418898,
         | 
| 44 | 
            +
                  2.735880826,
         | 
| 45 | 
            +
                  3.059592084,
         | 
| 46 | 
            +
                  3.421605075,
         | 
| 47 | 
            +
                  3.826451687,
         | 
| 48 | 
            +
                  4.279200023,
         | 
| 49 | 
            +
                  4.785517845,
         | 
| 50 | 
            +
                  5.351743533,
         | 
| 51 | 
            +
                  5.984965424,
         | 
| 52 | 
            +
                  6.693110555,
         | 
| 53 | 
            +
                  7.485043894,
         | 
| 54 | 
            +
                  8.370679318,
         | 
| 55 | 
            +
                  9.36110372,
         | 
| 56 | 
            +
                  10.4687158,
         | 
| 57 | 
            +
                  11.70738129,
         | 
| 58 | 
            +
                  13.09260651,
         | 
| 59 | 
            +
                  14.64173252,
         | 
| 60 | 
            +
                  16.37415215,
         | 
| 61 | 
            +
                  18.31155283,
         | 
| 62 | 
            +
                  20.47818807,
         | 
| 63 | 
            +
                  22.90118105,
         | 
| 64 | 
            +
                  25.61086418,
         | 
| 65 | 
            +
                  28.64115884,
         | 
| 66 | 
            +
                  32.03,
         | 
| 67 | 
            +
                  32.1,
         | 
| 68 | 
            +
                  32.13,
         | 
| 69 | 
            +
                  32.23,
         | 
| 70 | 
            +
                  32.6,
         | 
| 71 | 
            +
                  32.61,
         | 
| 72 | 
            +
                  32.64,
         | 
| 73 | 
            +
                  32.66,
         | 
| 74 | 
            +
                  32.7,
         | 
| 75 | 
            +
                  32.71,
         | 
| 76 | 
            +
                  32.93,
         | 
| 77 | 
            +
                  32.97,
         | 
| 78 | 
            +
                  33.28,
         | 
| 79 | 
            +
                  33.49,
         | 
| 80 | 
            +
                  33.5,
         | 
| 81 | 
            +
                  44.16,
         | 
| 82 | 
            +
                  47.77
         | 
| 83 | 
            +
                ],
         | 
| 84 | 
            +
                "short_factor": [
         | 
| 85 | 
            +
                  1.0,
         | 
| 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 | 
            +
                ],
         | 
| 134 | 
            +
                "type": "longrope"
         | 
| 135 | 
            +
              },
         | 
| 136 | 
            +
              "rope_theta": 10000.0,
         | 
| 137 | 
            +
              "sliding_window": 262144,
         | 
| 138 | 
            +
              "tie_word_embeddings": true,
         | 
| 139 | 
            +
              "torch_dtype": "bfloat16",
         | 
| 140 | 
            +
              "transformers_version": "4.52.4",
         | 
| 141 | 
            +
              "use_cache": true,
         | 
| 142 | 
            +
              "vocab_size": 200064
         | 
| 143 | 
            +
            }
         | 
