{
  "_name_or_path": "/tmp/transformers_cache/models--ibm-granite--granite-20b-functioncalling/snapshots/b030a7feff33cad1e2523fae857ef70bcce92e92",
  "activation_function": "gelu_pytorch_tanh",
  "architectures": [
    "GPTBigCodeForCausalLM"
  ],
  "attention_softmax_in_fp32": true,
  "attn_pdrop": 0.1,
  "bos_token_id": 0,
  "embd_pdrop": 0.1,
  "eos_token_id": 0,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt_bigcode",
  "multi_query": true,
  "n_embd": 6144,
  "n_head": 48,
  "n_inner": 24576,
  "n_layer": 52,
  "n_positions": 8192,
  "pad_token_id": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor",
          "symmetric": true,
          "type": "float"
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "tensor",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": 1.2470308756667798,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "resid_pdrop": 0.1,
  "scale_attention_softmax_in_fp32": true,
  "scale_attn_weights": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "vocab_size": 49152
}