config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/tmp/models/tmpfpody8xl/tmpo43hzpln",
  "_remove_final_layer_norm": false,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "architectures": [
    "OPTForCausalLM"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "do_layer_norm_before": true,
  "dropout": 0.1,
  "enable_bias": true,
  "eos_token_id": 2,
  "ffn_dim": 16384,
  "hidden_size": 4096,
  "init_std": 0.02,
  "layer_norm_elementwise_affine": true,
  "layerdrop": 0.0,
  "learned_embeddings": true,
  "max_position_embeddings": 2048,
  "model_type": "opt",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "pad_token_id": 1,
  "quantization_config": {
    "quant_config": {
      "offload_meta": false,
      "scale_quant_params": null,
      "weight_quant_params": {
        "axis": 1,
        "channel_wise": true,
        "group_size": 64,
        "nbits": 4,
        "optimize": true,
        "round_zero": true,
        "view_as_float": false
      },
      "zero_quant_params": null
    },
    "quant_method": "hqq",
    "skip_modules": [
      "lm_head"
    ]
  },
  "scale_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.48.2",
  "use_cache": true,
  "vocab_size": 50000,
  "word_embed_proj_dim": 4096
}