config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "shuyuej/c4ai-command-r7b-12-2024-GPTQ",
  "architectures": [
    "Cohere2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 5,
  "cache_implementation": "hybrid",
  "eos_token_id": 255001,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "layer_norm_eps": 1e-05,
  "layer_switch": 4,
  "logit_scale": 0.25,
  "max_position_embeddings": 8192,
  "model_type": "cohere2",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "order_of_interleaved_layers": "local_attn_first",
  "pad_token_id": 0,
  "position_embedding_type": "rope_gptj",
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "desc_act": true,
    "dynamic": null,
    "group_size": 128,
    "lm_head": false,
    "meta": {
      "damp_auto_increment": 0.0025,
      "damp_percent": 0.01,
      "mse": 0.0,
      "quantizer": [
        "gptqmodel:1.4.5"
      ],
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel"
    },
    "quant_method": "gptq",
    "sym": true
  },
  "rope_scaling": null,
  "rope_theta": 50000,
  "rotary_pct": 1.0,
  "sliding_window": 4096,
  "sliding_window_pattern": 4,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.0.dev0",
  "use_cache": true,
  "use_embedding_sharing": true,
  "use_gated_activation": true,
  "use_parallel_block": true,
  "use_parallel_embedding": true,
  "vocab_size": 256000
}