tarekziade HF Staff
Publish MIC usage, slim fixture and reviewed Transformers expectations
06ce3d5 verified Download config.json from huggingface-mic/Inkling-mic: direct link, hf CLI and curl.
- Browser
- Download file 3.54 kB
-
https://huggingface.co/huggingface-mic/Inkling-mic/resolve/main/config.json
- Command line
-
hf download hf://huggingface-mic/Inkling-mic/config.json
-
curl -L -o config.json https://huggingface.co/huggingface-mic/Inkling-mic/resolve/main/config.json
3.54 kB
| { | |
| "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": "float32", | |
| "initializer_range": 0.02, | |
| "mel_vocab_size": 16, | |
| "model_type": "inkling_audio", | |
| "n_mel_bins": 80, | |
| "rms_norm_eps": 1e-06, | |
| "text_hidden_size": 64, | |
| "use_audio_norm": true | |
| }, | |
| "audio_token_id": 200053, | |
| "dtype": "float32", | |
| "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 | |
| }, | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "chain_hidden_post_norm": false, | |
| "conv_kernel_size": 4, | |
| "d_rel": 16, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "final_logit_softcapping": null, | |
| "gate_activation": "sigmoid", | |
| "head_dim": 16, | |
| "hidden_act": "silu", | |
| "hidden_size": 64, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 128, | |
| "layer_types": [ | |
| "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", | |
| "sparse", | |
| "sparse" | |
| ], | |
| "model_type": "inkling_text", | |
| "moe_intermediate_size": 32, | |
| "mtp_hidden_states_first": true, | |
| "mtp_local_layer_ids": [ | |
| 0, | |
| 2, | |
| 4, | |
| 5, | |
| 6, | |
| 7 | |
| ], | |
| "n_routed_experts": 4, | |
| "n_shared_experts": 2, | |
| "norm_after_topk": true, | |
| "num_attention_heads": 4, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 3, | |
| "num_key_value_heads": 2, | |
| "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": 16, | |
| "swa_num_attention_heads": 2, | |
| "swa_num_key_value_heads": 2, | |
| "unpadded_vocab_size": 200058, | |
| "use_embed_norm": true, | |
| "use_gate_bias": true, | |
| "use_global_scale": true, | |
| "use_sconv": true, | |
| "vocab_size": 201024 | |
| }, | |
| "transformers_version": "5.22.0.dev0", | |
| "vision_config": { | |
| "decoder_dmodel": 6144, | |
| "dtype": "float32", | |
| "hidden_size": 64, | |
| "initializer_range": 0.02, | |
| "model_type": "inkling_vision", | |
| "n_channels": 3, | |
| "n_layers": 2, | |
| "num_attention_heads": 4, | |
| "num_channels": 3, | |
| "patch_size": 40, | |
| "rms_norm_eps": 1e-06, | |
| "temporal_patch_size": 2, | |
| "text_hidden_size": 64, | |
| "use_vision_norm": true, | |
| "vision_encoder_type": "hmlp" | |
| } | |
| } | |