{
  "_name_or_path": "delta-4b-notso-base",
  "architectures": [
    "PhiForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
  },
  "bos_token_id": 50256,
  "embd_pdrop": 0.0,
  "eos_token_id": 50256,
  "hidden_act": "gelu_new",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 10240,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "phi",
  "num_attention_heads": 32,
  "num_hidden_layers": 56,
  "num_key_value_heads": 32,
  "partial_rotary_factor": 0.4,
  "qk_layernorm": false,
  "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": 0.1,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "vocab_size": 51200
}