{ "attn_pdrop": 0.0, "scale_attn_weights": true, "resid_pdrop": 0.0, "mup_embeddings_scale": 14.6, "n_inner": 10922, "n_embd": 4096, "layer_norm_epsilon": 1e-05, "n_positions": 2048, "activation_function": "swiglu", "n_head": 32, "n_layer": 32, "mup_output_alpha": 2.22, "mup_width_scale": 0.0625, "position_embedding_type": "rotary", "rotary_dim": 32, "mup_scale_qk_dot_by_d": true, "tie_word_embeddings": true, "vocab_size": 32032, "embd_pdrop": 0.0, "model_type": "crystalcoder", "use_cache": true, "bos_token_id": 1, "eos_token_id": 2, "auto_map": { "AutoConfig": "configuration_crystalcoder.CrystalCoderConfig", "AutoModel": "modeling_crystalcoder.CrystalCoderModel", "AutoModelForCausalLM": "modeling_crystalcoder.CrystalCoderLMHeadModel" }, "architectures": [ "CrystalCoderLMHeadModel" ] }