Update tiny models for AudioFlamingo3Encoder

.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 a helpful assistant.<|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 +1,21 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "AudioFlamingo3Encoder"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "layerdrop": 0.0,
+  "max_source_positions": 200,
+  "model_type": "audioflamingo3_encoder",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_mel_bins": 80,
+  "scale_embedding": false,
+  "transformers_version": "5.16.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffe2a327d5aab71f6c4cbebba6af6f97765e5a3786be13a1767fd97be9349c6
+size 123888

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 sha256:1f14d54ac619b8d778bec7ddcc5d247a2148ffd16d1ee43a07d2d350bb4bec72
+size 11423182

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "processor_class": "AudioFlamingo3Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}