config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/home/ubuntu/.cache/pruna/tmp5u4v4d_o/tmpzr51qsp0",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 24,
  "num_key_value_heads": 32,
  "pad_token_id": 2,
  "pretraining_tp": 1,
  "quantization_config": {
    "quant_config": {
      "offload_meta": false,
      "scale_quant_params": null,
      "weight_quant_params": {
        "axis": 1,
        "channel_wise": true,
        "group_size": 64,
        "nbits": 8,
        "optimize": true,
        "round_zero": false,
        "view_as_float": false
      },
      "zero_quant_params": null
    },
    "quant_method": "hqq",
    "skip_modules": [
      "lm_head"
    ]
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 130000,
  "tie_word_embeddings": true,
  "torch_dtype": "float16",
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "4.46.3",
  "use_cache": true,
  "vocab_size": 49152
}