Upload folder using huggingface_hub

config.json

@@ -1,11 +1,86 @@
 {
-    "_name_or_path": "oriyonay/myna-base",
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "float32",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": true,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
     "architectures": [
         "Myna"
     ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": null,
+    "pad_token_id": null,
+    "eos_token_id": null,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "oriyonay/myna-base",
+    "transformers_version": "4.41.2",
+    "spec_size": [
+        128,
+        4096
+    ],
+    "patch_size": 16,
+    "dim": 384,
+    "depth": 12,
+    "heads": 6,
+    "mlp_dim": 1536,
+    "dim_head": 64,
+    "arch": "vit-s-16",
+    "additional_patch_size": null,
+    "hybrid_mode": false,
+    "n_samples": 50000,
+    "sr": 16000,
+    "n_frames": 96,
+    "model_type": "myna",
     "auto_map": {
         "AutoConfig": "myna.MynaConfig",
         "AutoModel": "myna.Myna"
-    },
-    "model_type": "myna"
+    }
 }

myna.py

@@ -20,7 +20,7 @@ import shutil
 
 
 def pair(t):
-    return t if isinstance(t, tuple) else (t, t)
+    return t if isinstance(t, (tuple, list)) else (t, t)
 
 
 def posemb_sincos_2d(h, w, dim, temperature: int = 10000, dtype = torch.float32):
@@ -268,7 +268,7 @@ class Myna(PreTrainedModel, PyTorchModelHubMixin):
 
     def _make_embeddings(self, patch_height, patch_width, patch_dim, dim, image_height, image_width):
         to_patch_embedding = nn.Sequential(
-            Rearrange("b c (h p1) (w p2) -> b (h w) (p1 p2 c)", p1 = patch_height, p2 = patch_width),
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
             nn.LayerNorm(patch_dim),
             nn.Linear(patch_dim, dim),
             nn.LayerNorm(dim),
@@ -286,7 +286,7 @@ class Myna(PreTrainedModel, PyTorchModelHubMixin):
         n_frames = self.config.n_frames
         if n_samples and n_samples != self.config.n_samples:
             n_frames = self.config._get_n_frames(n_samples)
-        spec = self.preprocessor(filename, n_frames)
+        spec = self.preprocessor(filename, n_frames).to(self.device)
         return self(spec)
 
     @property
@@ -298,7 +298,8 @@ def save_model_and_push(model, repo_name, save_dir='myna-temp', to_hub=False):
     model.save_pretrained(save_dir)
     shutil.copy('myna.py', save_dir)
 
-    config = {
+    config = model.config.to_dict()
+    config.update({
         '_name_or_path': repo_name,
         'architectures': ['Myna'],
         'auto_map': {
@@ -306,7 +307,7 @@ def save_model_and_push(model, repo_name, save_dir='myna-temp', to_hub=False):
             'AutoModel': 'myna.Myna'
         },
         'model_type': 'myna'
-    }
+    })
     
     with open(os.path.join(save_dir, 'config.json'), 'w') as f:
         json.dump(config, f, indent=4)
@@ -323,6 +324,7 @@ def save_model_and_push(model, repo_name, save_dir='myna-temp', to_hub=False):
 if __name__ == '__main__':
     config = MynaConfig(
         arch='vit-s-16',
+        patch_size=16,
         additional_patch_size=None,
         hybrid_mode=False
     )