{ "vocab_size": 84992, "embd_pdrop": 0.0, "tie_word_embeddings": true, "position_embedding_type": "alibi", "n_positions": 2048, "rotary_dim": null, "alibi_scaling": null, "n_embd": 1088, "n_layer": 14, "resid_pdrop": 0.0, "layer_norm_epsilon": 1e-05, "n_head": 17, "scale_attn_weights": true, "attn_pdrop": 0.0, "scale_attn_by_inverse_layer_idx": false, "n_inner": 2912, "activation_function": "swiglu", "mup_embeddings_scale": 9.1705785388303, "mup_scale_qk_dot_by_d": true, "mup_output_alpha": 1.09518349815769, "mup_width_scale": 0.23529411764705882, "initializer_range": 0.02, "model_type": "btlm", "use_cache": true, "auto_map": { "AutoConfig": "cerebras/btlm-3b-8k-base--configuration_btlm.BTLMConfig", "AutoModel": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMModel", "AutoModelForCausalLM": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMLMHeadModel" } }