config.json

{
  "apply_qk_norm": true,
  "architectures": [
    "OpenLMforCausalLM"
  ],
  "attn_func": null,
  "auto_map": {
    "AutoConfig": "configuration_openlm.OpenLMConfig",
    "AutoModel": "modeling_openlm.OpenLMModel",
    "AutoModelForCausalLM": "modeling_openlm.OpenLMforCausalLM"
  },
  "dim": 2560,
  "ffn_type": "swiglu",
  "model_type": "openlm",
  "moe_capacity_factor": 1.25,
  "moe_expert_model_parallelism": false,
  "moe_freq": 0,
  "moe_loss_weight": 0.1,
  "moe_num_experts": null,
  "moe_top_k": 2,
  "moe_weight_parallelism": false,
  "n_heads": 32,
  "n_layers": 32,
  "norm_eps": 1e-05,
  "norm_type": null,
  "params": null,
  "params_args_dict": {
    "apply_qk_norm": true,
    "attn_activation": null,
    "attn_name": "auto",
    "attn_seq_scalar": null,
    "attn_seq_scalar_alpha": null,
    "dim": 2560,
    "ffn_type": "swiglu",
    "model": "open_lm_3b",
    "model_norm": "gain_only_lp_layer_norm",
    "moe_capacity_factor": 1.25,
    "moe_expert_model_parallelism": false,
    "moe_freq": 0,
    "moe_loss_weight": 0.1,
    "moe_num_experts": null,
    "moe_top_k": 2,
    "moe_weight_parallelism": false,
    "n_heads": 32,
    "n_layers": 32,
    "norm_eps": 1e-05,
    "positional_embedding_type": "rotary",
    "post_embed_norm": false,
    "qk_norm": true,
    "seq_len": 2048,
    "vocab_size": 50432,
    "weight_tying": false
  },
  "positional_embedding_type": "rotary",
  "post_embed_norm": false,
  "seq_len": 2048,
  "tie_word_embeddings": false,
  "transformers_version": "4.40.0",
  "vocab_size": 50432,
  "weight_tying": false
}