Any-to-Any
Transformers
Safetensors
English
Korean
raon
feature-extraction
speech
audio
multimodal
mixture-of-experts
text-to-speech
automatic-speech-recognition
custom_code
Instructions to use KRAFTON/A.X-K2-Raon-Speech-21B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KRAFTON/A.X-K2-Raon-Speech-21B-A3B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("KRAFTON/A.X-K2-Raon-Speech-21B-A3B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "", | |
| "accept_hidden_layer": -1, | |
| "acoustic_delay": null, | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "RaonModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_raon.RaonConfig", | |
| "AutoModel": "modeling_raon.RaonModel", | |
| "AutoModelForCausalLM": "modeling_raon.RaonModel" | |
| }, | |
| "audio_input_token_id": 163844, | |
| "audio_output_token_id": 163843, | |
| "audio_start_token_id": 163840, | |
| "audio_encoder_config": { | |
| "_name_or_path": "", | |
| "activation_dropout": 0, | |
| "activation_function": "gelu", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "conv_chunksize": 500, | |
| "cross_attention_hidden_size": null, | |
| "d_model": 1024, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "downsample_hidden_size": 480, | |
| "dropout": 0, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layers": 24, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_source_positions": 1500, | |
| "min_length": 0, | |
| "model_type": "qwen3_omni_moe_audio_encoder", | |
| "n_window": 50, | |
| "n_window_infer": 800, | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 24, | |
| "num_mel_bins": 128, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_dim": 2048, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 163692, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sampling_rate": 24000, | |
| "scale_embedding": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "audio_tokenizer_config": { | |
| "_frame_rate": 12.5, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "MimiModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "audio_channels": 1, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "codebook_dim": 256, | |
| "codebook_size": 2048, | |
| "compress": 2, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "dilation_growth_rate": 2, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 64, | |
| "hidden_act": "gelu", | |
| "hidden_size": 512, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "kernel_size": 7, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "last_kernel_size": 3, | |
| "layer_scale_initial_scale": 0.01, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 8000, | |
| "min_length": 0, | |
| "model_type": "mimi", | |
| "no_repeat_ngram_size": 0, | |
| "norm_eps": 1e-05, | |
| "normalize": false, | |
| "num_attention_heads": 8, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_filters": 64, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 8, | |
| "num_quantizers": 32, | |
| "num_residual_layers": 1, | |
| "num_return_sequences": 1, | |
| "num_semantic_quantizers": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_mode": "constant", | |
| "pad_token_id": 163692, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "residual_kernel_size": 3, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rope_theta": 10000.0, | |
| "sampling_rate": 24000, | |
| "sep_token_id": null, | |
| "sliding_window": 250, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "trim_right_ratio": 1.0, | |
| "typical_p": 1.0, | |
| "upsample_groups": 512, | |
| "upsampling_ratios": [ | |
| 8, | |
| 6, | |
| 5, | |
| 4 | |
| ], | |
| "use_bfloat16": true, | |
| "use_cache": false, | |
| "use_causal_conv": true, | |
| "use_conv_shortcut": false, | |
| "use_streaming": false, | |
| "vector_quantization_hidden_dimension": 256 | |
| }, | |
| "aut_is_causal": false, | |
| "axk1_native_token_ids": { | |
| "im_end": 163704, | |
| "im_start": 163702, | |
| "pad": 163692, | |
| "think": 163705, | |
| "think_end": 163706 | |
| }, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "code_predictor_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "min_length": 0, | |
| "model_type": "qwen3_omni_moe_talker_code_predictor", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_code_groups": 16, | |
| "num_hidden_layers": 5, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 163692, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sep_token_id": null, | |
| "sliding_window": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": true, | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 2048 | |
| }, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": "bfloat16", | |
| "duplex_token_ids": { | |
| "<|audio_end|>": 163841, | |
| "<|audio_input_placeholder|>": 163844, | |
| "<|audio_output_end_pad|>": 163846, | |
| "<|audio_output_pad|>": 163845, | |
| "<|audio_output_placeholder|>": 163843, | |
| "<|audio_start|>": 163840, | |
| "<|speaker_embedding_placeholder|>": 163842 | |
| }, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_size": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "input_adaptor_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_config": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_size": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "input_size": 2048, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "embedding_adaptor", | |
| "no_repeat_ngram_size": 0, | |
| "norm_eps": 1e-06, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_layers": 2, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "output_size": 2048, | |
| "output_time_scale": 1, | |
| "pad_token_id": null, | |
| "post_norm_init_scale": 0.024521998903, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_post_norm": true, | |
| "use_residual": false | |
| }, | |
| "input_num_code_groups": 8, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "keys_to_ignore_at_inference": [ | |
| "past_key_values" | |
| ], | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_audio_output_seq_length": 192000, | |
| "max_audio_seq_length": 192000, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "duplex_bc_token_id": -1, | |
| "duplex_end_pad_token_id": 163846, | |
| "duplex_pad_token_id": 163845, | |
| "duplex_sil_token_id": -1, | |
| "im_start_token_id": 163702, | |
| "model_type": "raon", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "num_talker_layers": 4, | |
| "output_adaptor_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_config": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_size": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "input_size": 512, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "embedding_adaptor", | |
| "no_repeat_ngram_size": 0, | |
| "norm_eps": 1e-06, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_layers": 2, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "output_size": 2048, | |
| "output_time_scale": 1, | |
| "pad_token_id": null, | |
| "post_norm_init_scale": 0.023371641436, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_post_norm": true, | |
| "use_residual": false | |
| }, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 163692, | |
| "prefix": null, | |
| "problem_type": null, | |
| "proj_code_bias": true, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rope_scaling": { | |
| "beta_fast": 32, | |
| "beta_slow": 1, | |
| "factor": 32, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "rope_type": "yarn", | |
| "type": "yarn" | |
| }, | |
| "sep_token_id": null, | |
| "speaker_encoder_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": null, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "encoder_type": "ecapa_tdnn", | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "frame_rate": 12.5, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "input_size": 512, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_seconds": 10.0, | |
| "min_length": 0, | |
| "min_seconds": 2.0, | |
| "model_type": "speaker_encoder", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "output_size": 2048, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "pretrained_dim": 192, | |
| "pretrained_model_id": "speechbrain/spkrec-ecapa-voxceleb", | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "speaker_token_id": 163842, | |
| "supports_audio_input": true, | |
| "supports_audio_output": true, | |
| "suppress_tokens": null, | |
| "talker_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": null, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "min_length": 0, | |
| "model_type": "qwen3", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "sep_token_id": null, | |
| "sliding_window": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 153723 | |
| }, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "text_model_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "AXK1ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_axk1.AXK1Config", | |
| "AutoModel": "modeling_axk1.AXK1Model", | |
| "AutoModelForCausalLM": "modeling_axk1.AXK1ForCausalLM" | |
| }, | |
| "aux_loss_alpha": 0.0001, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 163691, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 163704, | |
| "ep_size": 1, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "first_k_dense_replace": 1, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "kv_lora_rank": 128, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 131072, | |
| "min_length": 0, | |
| "model_name": "A.X-K1-Light-r260527", | |
| "model_type": "AXK1", | |
| "moe_intermediate_size": 512, | |
| "moe_layer_freq": 1, | |
| "n_group": 8, | |
| "n_routed_experts": 128, | |
| "n_shared_experts": 1, | |
| "no_repeat_ngram_size": 0, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 32, | |
| "num_nextn_predict_layers": 0, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 163692, | |
| "prefix": null, | |
| "pretraining_tp": 1, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "q_lora_rank": 384, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "beta_fast": 32, | |
| "beta_slow": 1, | |
| "factor": 32, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 10000, | |
| "routed_scaling_factor": 2.5, | |
| "scoring_func": "sigmoid", | |
| "sep_token_id": null, | |
| "seq_aux": true, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "topk_group": 4, | |
| "topk_method": "noaux_tc", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "v_head_dim": 128, | |
| "vocab_size": 163847 | |
| }, | |
| "text_model_path": "", | |
| "tf_legacy_loss": false, | |
| "thinker_to_talker_intermediate_size": 6144, | |
| "thinker_to_talker_pre_norm": false, | |
| "thinker_to_talker_projection_mode": "mlp", | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "transformers_version": "4.57.1", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_duplex_end_pad": false, | |
| "use_inline_text_prediction": false | |
| } | |