| { |
| "architectures": [ |
| "InklingForConditionalGeneration" |
| ], |
| "audio_config": { |
| "audio_mode": "dmel", |
| "bias": false, |
| "decoder_dmodel": 6144, |
| "dmel_max_value": 2.0, |
| "dmel_min_value": -7.0, |
| "mel_vocab_size": 16, |
| "n_mel_bins": 80, |
| "use_audio_norm": true |
| }, |
| "eos_token_id": 200006, |
| "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": { |
| "config_group_0": { |
| "format": "float-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": true, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": null, |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "token", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "channel", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "float-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.llm.unembed", |
| "model.llm.embed", |
| "re:.*norm.*", |
| "re:.*bias$", |
| "re:.*\\.attn$", |
| "re:.*\\.attn\\..*", |
| "re:.*sconv$", |
| "re:.*\\.gate$", |
| "re:.*global_scale$", |
| "re:.*shared_experts.*", |
| "re:model\\.layers\\.[01]\\.mlp\\..*", |
| "re:model\\.layers\\.2\\.mlp\\.experts\\..*", |
| "re:model\\.visual\\..*", |
| "re:model\\.audio\\..*" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "transform_config": {}, |
| "version": "0.17.2.a20260714" |
| }, |
| "text_config": { |
| "d_rel": 16, |
| "dense_intermediate_size": 24576, |
| "dense_mlp_idx": 2, |
| "final_logit_softcapping": null, |
| "gate_activation": "sigmoid", |
| "head_dim": 128, |
| "hidden_size": 6144, |
| "intermediate_size": 3072, |
| "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, |
| "model_max_length": 1048576, |
| "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, |
| "o_bias": false, |
| "q_bias": false, |
| "rel_extent": 1024, |
| "rms_norm_eps": 1e-06, |
| "route_scale": 8.0, |
| "sconv_kernel_size": 4, |
| "shared_expert_sink": true, |
| "sliding_window_size": 512, |
| "swa_head_dim": 128, |
| "swa_num_attention_heads": 64, |
| "swa_num_key_value_heads": 16, |
| "torch_dtype": "bfloat16", |
| "unpadded_vocab_size": 200058, |
| "use_embed_norm": true, |
| "use_gate_bias": true, |
| "use_global_scale": true, |
| "use_sconv": true, |
| "vocab_size": 201024 |
| }, |
| "vision_config": { |
| "decoder_dmodel": 6144, |
| "n_channels": 3, |
| "n_layers": 4, |
| "patch_size": 40, |
| "temporal_patch_size": 2, |
| "use_vision_norm": true, |
| "vision_encoder_type": "hmlp" |
| } |
| } |
