{ "architectures": [ "InklingForConditionalGeneration" ], "audio_bos_token_id": 200020, "audio_config": { "audio_mode": "dmel", "bias": false, "decoder_dmodel": 6144, "dmel_max_value": 2.0, "dmel_min_value": -7.0, "dtype": "bfloat16", "initializer_range": 0.02, "mel_vocab_size": 16, "model_type": "inkling_audio", "n_mel_bins": 80, "rms_norm_eps": 1e-06, "text_hidden_size": 6144, "use_audio_norm": true }, "audio_token_id": 200053, "dtype": "bfloat16", "eos_token_id": 200006, "image_bos_token_id": 200005, "image_token_id": 200054, "model_type": "inkling_mm_model", "mtp_config": { "chain_hidden_post_norm": false, "local_layer_ids": [ 0, 2, 4, 5, 6, 7 ], "num_nextn_predict_layers": 8 }, "quantization_config": { "config_groups": { "group_0": { "format": "float-quantized", "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": 128, "num_bits": 8, "observer": null, "observer_kwargs": {}, "scale_dtype": null, "strategy": "group", "symmetric": true, "type": "float", "zp_dtype": null }, "output_activations": null, "targets": [ "re:.*attn\\..*" ], "weights": { "actorder": null, "block_structure": [ 128, 128 ], "dynamic": false, "group_size": null, "num_bits": 8, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": null, "strategy": "block", "symmetric": true, "type": "float", "zp_dtype": null } }, "group_1": { "format": "nvfp4-pack-quantized", "input_activations": { "actorder": null, "block_structure": null, "dynamic": "local", "group_size": 16, "num_bits": 4, "observer": "static_minmax", "observer_kwargs": {}, "scale_dtype": "torch.float8_e4m3fn", "strategy": "tensor_group", "symmetric": true, "type": "float", "zp_dtype": null }, "output_activations": null, "targets": [ "re:.*mlp\\.(?!shared_experts).*" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 16, "num_bits": 4, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": "torch.float8_e4m3fn", "strategy": "tensor_group", "symmetric": true, "type": "float", "zp_dtype": null } }, "group_2": { "format": "float-quantized", "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": 128, "num_bits": 8, "observer": null, "observer_kwargs": {}, "scale_dtype": null, "strategy": "group", "symmetric": true, "type": "float", "zp_dtype": null }, "output_activations": null, "targets": [ "re:.*shared_experts.*" ], "weights": { "actorder": null, "block_structure": [ 128, 128 ], "dynamic": false, "group_size": null, "num_bits": 8, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": null, "strategy": "block", "symmetric": true, "type": "float", "zp_dtype": null } } }, "format": "mixed-precision", "global_compression_ratio": null, "ignore": [ "model.llm.layers.2.mlp.gate", "model.llm.layers.3.mlp.gate", "model.llm.layers.4.mlp.gate", "model.llm.layers.5.mlp.gate", "model.llm.layers.6.mlp.gate", "model.llm.layers.7.mlp.gate", "model.llm.layers.8.mlp.gate", "model.llm.layers.9.mlp.gate", "model.llm.layers.10.mlp.gate", "model.llm.layers.11.mlp.gate", "model.llm.layers.12.mlp.gate", "model.llm.layers.13.mlp.gate", "model.llm.layers.14.mlp.gate", "model.llm.layers.15.mlp.gate", "model.llm.layers.16.mlp.gate", "model.llm.layers.17.mlp.gate", "model.llm.layers.18.mlp.gate", "model.llm.layers.19.mlp.gate", "model.llm.layers.20.mlp.gate", "model.llm.layers.21.mlp.gate", "model.llm.layers.22.mlp.gate", "model.llm.layers.23.mlp.gate", "model.llm.layers.24.mlp.gate", "model.llm.layers.25.mlp.gate", "model.llm.layers.26.mlp.gate", "model.llm.layers.27.mlp.gate", "model.llm.layers.28.mlp.gate", "model.llm.layers.29.mlp.gate", "model.llm.layers.30.mlp.gate", "model.llm.layers.31.mlp.gate", "model.llm.layers.32.mlp.gate", "model.llm.layers.33.mlp.gate", "model.llm.layers.34.mlp.gate", "model.llm.layers.35.mlp.gate", "model.llm.layers.36.mlp.gate", "model.llm.layers.37.mlp.gate", "model.llm.layers.38.mlp.gate", "model.llm.layers.39.mlp.gate", "model.llm.layers.40.mlp.gate", "model.llm.layers.41.mlp.gate", "model.llm.layers.42.mlp.gate", "model.llm.layers.43.mlp.gate", "model.llm.layers.44.mlp.gate", "model.llm.layers.45.mlp.gate", "model.llm.layers.46.mlp.gate", "model.llm.layers.47.mlp.gate", "model.llm.layers.48.mlp.gate", "model.llm.layers.49.mlp.gate", "model.llm.layers.50.mlp.gate", "model.llm.layers.51.mlp.gate", "model.llm.layers.52.mlp.gate", "model.llm.layers.53.mlp.gate", "model.llm.layers.54.mlp.gate", "model.llm.layers.55.mlp.gate", "model.llm.layers.56.mlp.gate", "model.llm.layers.57.mlp.gate", "model.llm.layers.58.mlp.gate", "model.llm.layers.59.mlp.gate", "model.llm.layers.60.mlp.gate", "model.llm.layers.61.mlp.gate", "model.llm.layers.62.mlp.gate", "model.llm.layers.63.mlp.gate", "model.llm.layers.64.mlp.gate", "model.llm.layers.65.mlp.gate", "model.visual.layers.linear_0", "model.visual.layers.linear_1", "model.visual.layers.linear_2", "model.visual.layers.linear_3", "lm_head", "re:^model.mtp.*" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.17.2.dev28+gbf810058.d20260720" }, "text_config": { "attention_dropout": 0.0, "bos_token_id": 1, "chain_hidden_post_norm": false, "conv_kernel_size": 4, "dense_mlp_idx": 2, "d_rel": 16, "dtype": "bfloat16", "eos_token_id": 2, "final_logit_softcapping": null, "gate_activation": "sigmoid", "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 24576, "layer_types": [ "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid_sliding", "hybrid" ], "local_layer_ids": [ 0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 54, 55, 56, 57, 58, 60, 61, 62, 63, 64 ], "log_scaling_alpha": 0.1, "log_scaling_n_floor": 128000, "logits_mup_width_multiplier": 24.0, "max_position_embeddings": 1048576, "mlp_layer_types": [ "dense", "dense", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse" ], "model_type": "inkling_text", "moe_intermediate_size": 3072, "mtp_hidden_states_first": true, "mtp_local_layer_ids": [ 0, 2, 4, 5, 6, 7 ], "n_routed_experts": 256, "n_shared_experts": 2, "norm_after_topk": true, "num_attention_heads": 64, "num_experts_per_tok": 6, "num_hidden_layers": 66, "num_key_value_heads": 8, "num_mtp_layers": 8, "number_of_conv_states": 4, "o_bias": false, "pad_token_id": null, "q_bias": false, "rel_extent": 1024, "rms_norm_eps": 1e-06, "rms_norm_eps_moe_gate": 1e-06, "route_scale": 8.0, "shared_expert_sink": true, "sliding_window_size": 512, "swa_head_dim": 128, "swa_num_attention_heads": 64, "swa_num_key_value_heads": 16, "unpadded_vocab_size": 200058, "use_embed_norm": true, "use_gate_bias": true, "use_global_scale": true, "use_sconv": true, "vocab_size": 201024 }, "transformers_version": "5.14.1", "vision_config": { "decoder_dmodel": 6144, "dtype": "bfloat16", "hidden_size": 1024, "initializer_range": 0.02, "model_type": "inkling_vision", "n_channels": 3, "n_layers": 4, "num_attention_heads": 16, "num_channels": 3, "patch_size": 40, "rms_norm_eps": 1e-06, "temporal_patch_size": 2, "text_hidden_size": 6144, "use_vision_norm": true, "vision_encoder_type": "hmlp" } }