config.json

{
  "_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsi0oo5km_plq2xye6",
  "architectures": [
    "Phi3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_phi3.Phi3Config",
    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
  },
  "bos_token_id": 1,
  "embd_pdrop": 0.0,
  "eos_token_id": 32000,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "model_type": "phi3",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 32000,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "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": [
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1.0700000524520874,
      1.1200000047683716,
      1.149999976158142,
      1.4199999570846558,
      1.5699999332427979,
      1.7999999523162842,
      2.129999876022339,
      2.129999876022339,
      3.009999990463257,
      5.910000324249268,
      6.950000286102295,
      9.070000648498535,
      9.930000305175781,
      10.710000038146973,
      11.130000114440918,
      14.609999656677246,
      15.409998893737793,
      19.809999465942383,
      37.279998779296875,
      38.279998779296875,
      38.599998474121094,
      40.12000274658203,
      46.20000457763672,
      50.940006256103516,
      53.66000747680664,
      54.9373893737793,
      56.89738845825195,
      57.28738784790039,
      59.98738479614258,
      60.86738586425781,
      60.887386322021484,
      61.71739196777344,
      62.91739273071289,
      62.957393646240234,
      63.41739273071289,
      63.8173942565918,
      63.83739471435547,
      63.897396087646484,
      63.93739700317383,
      64.06739807128906,
      64.11434936523438,
      64.12435150146484,
      64.15435028076172,
      64.19435119628906,
      64.24435424804688,
      64.57435607910156,
      64.69000244140625,
      64.76000213623047
    ],
    "short_factor": [
      1.1,
      1.1,
      1.1,
      1.3000000000000003,
      1.3500000000000003,
      1.3500000000000003,
      1.4000000000000004,
      1.5500000000000005,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.000000000000001,
      2.0500000000000007,
      2.0500000000000007,
      2.0500000000000007,
      2.0500000000000007,
      2.0500000000000007,
      2.0500000000000007,
      2.1000000000000005,
      2.1000000000000005,
      2.1500000000000004,
      2.25,
      2.25,
      2.25,
      2.25,
      2.25,
      2.3999999999999995,
      2.4499999999999993,
      2.499999999999999,
      2.6999999999999984,
      2.6999999999999984,
      2.7499999999999982,
      2.799999999999998,
      2.8999999999999977,
      3.049999999999997
    ],
    "type": "longrope"
  },
  "rope_theta": 10000.0,
  "sliding_window": 262144,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.42.4",
  "use_cache": true,
  "vocab_size": 32064
}