demo: tokenizer config.json

tokenizer/config.json

@@ -0,0 +1,197 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "MossTTSNanoForCausalLM"
+  ],
+  "attn_implementation": "flash_attention_2",
+  "audio_assistant_slot_token_id": 9,
+  "audio_codebook_sizes": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "audio_end_token_id": 7,
+  "audio_pad_token_id": 1024,
+  "audio_start_token_id": 6,
+  "audio_tokenizer_pretrained_name_or_path": "OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano",
+  "audio_tokenizer_sample_rate": 48000,
+  "audio_tokenizer_type": "moss-audio-tokenizer-nano",
+  "audio_user_slot_token_id": 8,
+  "audio_vocab_size": 1024,
+  "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": "float32",
+  "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,
+  "gpt2_config": {
+    "_name_or_path": "",
+    "activation_function": "gelu_new",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attn_pdrop": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "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,
+    "embd_pdrop": 0.0,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "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
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 32768,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": 3072,
+    "n_layer": 12,
+    "n_positions": 32768,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 3,
+    "position_embedding_type": "rope",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_base": 10000.0,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "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,
+    "transformers_version": "4.57.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 16384
+  },
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "im_end_token_id": 5,
+  "im_start_token_id": 4,
+  "initializer_range": 0.02,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "length_penalty": 1.0,
+  "local_transformer_attn_implementation": "flash_attention_2",
+  "local_transformer_layers": 1,
+  "max_length": 20,
+  "max_position_embeddings": 32768,
+  "min_length": 0,
+  "model_architecture": "global_local_transformer",
+  "model_type": "moss_tts_nano",
+  "n_vq": 16,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 3,
+  "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": "MossTTSNanoSentencePieceTokenizer",
+  "tokenizer_use_fast": false,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "transformers_version": "4.57.1",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "vocab_size": 16384,
+  "auto_map": {
+    "AutoConfig": "configuration_moss_tts_nano.MossTTSNanoConfig",
+    "AutoModel": "modeling_moss_tts_nano.MossTTSNanoForCausalLM",
+    "AutoModelForCausalLM": "modeling_moss_tts_nano.MossTTSNanoForCausalLM"
+  }
+}