{ "_name_or_path": "apple/OpenELM-450M-Instruct", "activation_fn_name": "swish", "architectures": [ "LlavaOpenELMForCausalLM" ], "auto_map": { "AutoConfig": "configuration_openelm.OpenELMConfig", "AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM" }, "bos_token_id": 1, "eos_token_id": 2, "ffn_dim_divisor": 256, "ffn_multipliers": [ 0.5, 0.68, 0.87, 1.05, 1.24, 1.42, 1.61, 1.79, 1.97, 2.16, 2.34, 2.53, 2.71, 2.89, 3.08, 3.26, 3.45, 3.63, 3.82, 4.0 ], "ffn_with_glu": true, "freeze_mm_mlp_adapter": false, "head_dim": 64, "hidden_size": 1536, "image_aspect_ratio": "anyres", "image_grid_pinpoints": [[224, 224], [224, 448], [448, 224], [448, 448], [448, 672], [672, 448], [672, 672], [672, 896], [896, 672]], "initializer_range": 0.02, "max_context_length": 2048, "mm_hidden_size": 768, "mm_patch_merge_type": "spatial", "mm_projector_lr": null, "mm_projector_type": "mlp2x_gelu", "mm_use_im_patch_token": false, "mm_use_im_start_end": false, "mm_vision_select_feature": "patch", "mm_vision_select_layer": -2, "mm_vision_tower": "gwkrsrch/elva-encoder-base-patch32", "mm_vision_tower_lr": null, "model_dim": 1536, "model_type": "llava_openelm", "normalization_layer_name": "rms_norm", "normalize_qk_projections": true, "num_gqa_groups": 4, "num_kv_heads": [ 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6 ], "num_query_heads": [ 12, 12, 12, 16, 16, 16, 16, 16, 16, 16, 20, 20, 20, 20, 20, 20, 24, 24, 24, 24 ], "num_transformer_layers": 20, "qkv_multipliers": [ 0.5, 1.0 ], "rope_freq_constant": 10000, "rope_max_length": 4096, "share_input_output_layers": true, "tokenizer_model_max_length": 2048, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.42.4", "tune_mm_mlp_adapter": false, "use_cache": true, "use_mm_proj": true, "vocab_size": 32000 }