Upload MoshiForConditionalGeneration

config.json

@@ -3,7 +3,7 @@
     "MoshiForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "audio_encoder": {
+  "audio_encoder_config": {
     "_name_or_path": "kyutai/mimi",
     "add_cross_attention": false,
     "architectures": [
@@ -112,14 +112,86 @@
     "vector_quantization_hidden_dimension": 256
   },
   "audio_vocab_size": 2048,
-  "depth_ffn_dim": 5632,
-  "depth_head_dim": 64,
-  "depth_hidden_size": 1024,
-  "depth_max_position_embeddings": 9,
-  "depth_num_attention_heads": 16,
-  "depth_num_hidden_layers": 6,
-  "depth_num_key_value_heads": 16,
-  "depth_sliding_window": 8,
+  "depth_decoder_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "audio_vocab_size": 2048,
+    "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,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 5632,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "input_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 9,
+    "min_length": 0,
+    "model_type": "moshi_depth",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 8,
+    "num_hidden_layers": 6,
+    "num_key_value_heads": 16,
+    "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-08,
+    "sep_token_id": null,
+    "sliding_window": 8,
+    "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,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
   "ffn_dim": 22528,
   "head_dim": 128,
   "hidden_act": "silu",