Update tiny models for MusicFlamingoModel

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,6 @@
+{% if messages[0]['role'] != 'system' %}<|im_start|>system
+You are Music Flamingo, a multimodal assistant for language and music. On each turn you receive an audio clip which contains music and optional text, you will receive at least one or both; use your world knowledge and reasoning to help the user with any task. Interpret the entirety of the content any input music--regardlenss of whether the user calls it audio, music, or sound.<|im_end|>
+{% endif %}{% for m in messages if m['content'] is not none %}<|im_start|>{{ m['role'] }}
+{% if m['content'] is string %}{{ m['content'] }}{% else %}{% set audio = namespace(found=False) %}{% set text_buf = namespace(v='') %}{% for c in m['content'] %}{% if c.get('type') == 'audio' or 'audio' in c %}{% set audio.found = True %}{% elif c.get('type') == 'text' or 'text' in c %}{% set text_buf.v = text_buf.v + c['text'] %}{% endif %}{% endfor %}{% if audio.found %}{{ '<sound>' }}{% endif %}{{ text_buf.v }}{% endif %}<|im_end|>
+{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "MusicFlamingoModel"
+  ],
+  "audio_bos_token_id": 151670,
+  "audio_config": {
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layerdrop": 0.0,
+    "max_source_positions": 30,
+    "model_type": "audioflamingo3_encoder",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_mel_bins": 80,
+    "scale_embedding": false
+  },
+  "audio_eos_token_id": 151671,
+  "audio_frame_step": 0.01,
+  "audio_token_id": 0,
+  "dtype": "float32",
+  "head_dim": 32,
+  "max_position_embeddings": 512,
+  "model_type": "musicflamingo",
+  "pad_token_id": 151669,
+  "projector_bias": true,
+  "projector_hidden_act": "gelu",
+  "rope_parameters": {
+    "partial_rotary_factor": 0.5,
+    "rope_theta": 2048,
+    "rope_type": "default"
+  },
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 151668,
+    "eos_token_id": 151645,
+    "hidden_act": "gelu",
+    "hidden_size": 32,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layer_types": [
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 512,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151669,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151672
+  },
+  "transformers_version": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ab9ea4e28933a546b19f9de191abf2a4ce4fece57a6fbfa2fe1729294bf019
+size 19587296

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a64cc913679c6eaf01ba137504e15a55d174d590944fe06f7b3899b2ae82de31
+size 11423197

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|sound_bos|>",
+    "<|sound_eos|>"
+  ],
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "processor_class": "MusicFlamingoProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}