config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "migtissera/Tess-v2.5-Phi-3-medium-128k-14B",
  "architectures": [
    "Phi3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "microsoft/Phi-3-medium-128k-instruct--configuration_phi3.Phi3Config",
    "AutoModelForCausalLM": "microsoft/Phi-3-medium-128k-instruct--modeling_phi3.Phi3ForCausalLM"
  },
  "bos_token_id": 1,
  "embd_pdrop": 0.0,
  "eos_token_id": 32011,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 17920,
  "max_position_embeddings": 131072,
  "model_type": "phi3",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "num_key_value_heads": 10,
  "original_max_position_embeddings": 4096,
  "pad_token_id": null,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.25,
      1.25,
      1.5,
      2.0,
      2.75,
      5.75,
      5.75,
      6.5,
      9.25,
      11.0,
      13.25,
      19.25,
      19.75,
      19.75,
      21.25,
      21.5,
      26.5,
      30.0,
      33.75,
      35.25,
      38.5,
      42.0,
      42.25,
      46.0,
      47.0,
      50.0,
      50.5,
      51.0,
      52.0,
      52.75,
      53.75,
      54.75,
      57.0,
      57.25,
      58.5,
      59.25,
      59.5,
      62.0,
      62.5,
      62.75,
      63.25,
      63.25,
      63.25,
      63.75,
      64.0,
      64.0,
      64.25,
      64.5,
      64.5,
      65.0,
      65.0
    ],
    "short_factor": [
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.01,
      1.02,
      1.02,
      1.04,
      1.04,
      1.07,
      1.07,
      1.1,
      1.3000000000000003,
      1.3000000000000003,
      1.5000000000000004,
      1.5700000000000005,
      1.9000000000000008,
      2.3100000000000014,
      2.759999999999992,
      3.3899999999999784,
      3.9399999999999666,
      4.009999999999965,
      4.289999999999959,
      4.349999999999958,
      5.349999999999937,
      6.659999999999909,
      7.029999999999901,
      7.51999999999989,
      8.00999999999988,
      8.249999999999876,
      8.279999999999875,
      9.629999999999846,
      9.89999999999984,
      10.589999999999826,
      11.049999999999816,
      11.7899999999998,
      12.189999999999792,
      12.889999999999777,
      13.129999999999772,
      13.16999999999977,
      13.20999999999977,
      13.479999999999764,
      13.539999999999763,
      13.779999999999758,
      13.929999999999755,
      14.429999999999744,
      14.759999999999737,
      15.149999999999729,
      15.419999999999723,
      15.53999999999972,
      15.659999999999718,
      15.749999999999716,
      15.759999999999716,
      15.799999999999715,
      16.05999999999971,
      16.079999999999714,
      16.11999999999972,
      16.11999999999972,
      16.18999999999973,
      16.31999999999975,
      16.539999999999786,
      16.799999999999827
    ],
    "type": "su"
  },
  "rope_theta": 10000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.0",
  "use_cache": false,
  "vocab_size": 32064
}