meta.json

{
 "expert_bits": 2,
 "resident_bits": 4,
 "group_size": 64,
 "num_layers": 32,
 "num_experts": 128,
 "text_config": {
  "_sliding_window_pattern": 4,
  "add_cross_attention": false,
  "architectures": [
   "Cohere2MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "cross_attention_hidden_size": null,
  "decoder_start_token_id": null,
  "dtype": "bfloat16",
  "eos_token_id": 255001,
  "expert_selection_fn": "sigmoid",
  "finetuning_task": null,
  "first_k_dense_replace": 0,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "is_decoder": false,
  "layer_norm_eps": 1e-05,
  "layer_switch": 4,
  "layer_types": [
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention",
   "sliding_attention",
   "sliding_attention",
   "sliding_attention",
   "full_attention"
  ],
  "logit_scale": 1.0,
  "max_position_embeddings": 5000000,
  "model_type": "cohere2_moe",
  "norm_topk_prob": true,
  "num_attention_heads": 128,
  "num_experts": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "num_shared_experts": 4,
  "order_of_interleaved_layers": "local_attn_first",
  "pad_token_id": 0,
  "position_embedding_type": "rope_gptj",
  "prefix": null,
  "prefix_dense_intermediate_size": 16384,
  "prefix_dense_sliding_window_pattern": 1,
  "pruned_heads": {},
  "rms_norm_eps": null,
  "rope_parameters": {
   "rope_theta": 50000,
   "rope_type": "default"
  },
  "rope_theta": 50000,
  "rotary_pct": 1.0,
  "sep_token_id": null,
  "shared_expert_combination_strategy": "average",
  "sliding_window": 4096,
  "task_specific_params": null,
  "tf_legacy_loss": false,
  "tie_encoder_decoder": false,
  "tie_word_embeddings": true,
  "tokenizer_class": null,
  "torchscript": false,
  "use_bfloat16": false,
  "use_cache": true,
  "use_embedding_sharing": true,
  "use_gated_activation": true,
  "use_parallel_block": true,
  "use_parallel_embedding": false,
  "use_qk_norm": false,
  "vocab_size": 262144
 }
}