Add HF compatible checkpoints (#6)

- Update model (b115745955868fa9e30caa4fd8e841ea938fc8a1)


Co-authored-by: Yaswanth <yaswanthgali@users.noreply.huggingface.co>

config.json

@@ -1,169 +1,57 @@
 {
   "architectures": [
-    "AIMv2Model"
+    "Aimv2Model"
   ],
   "auto_map": {
     "AutoConfig": "configuration_aimv2.AIMv2Config",
     "AutoModel": "modeling_aimv2.AIMv2Model"
   },
   "init_temperature": 0.07,
+  "logit_scale_init_value": 2.6592,
   "max_logit_scale": 100.0,
   "model_type": "aimv2",
   "projection_dim": 768,
   "text_config": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
     "attention_dropout": 0.0,
-    "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": 49407,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
+    "hidden_act": "silu",
     "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
+    "initializer_range": 0.02,
     "intermediate_size": 2048,
     "is_causal": true,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
     "max_context_length": 77,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "aimv2",
-    "no_repeat_ngram_size": 0,
+    "max_position_embeddings": 77,
+    "mlp_bias": false,
+    "model_type": "aimv2_text_model",
     "num_attention_heads": 6,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "problem_type": null,
     "projection_dropout": 0.0,
-    "pruned_heads": {},
     "qkv_bias": false,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
-    "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": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
     "use_bias": false,
     "vocab_size": 49408
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.54.0.dev0",
   "vision_config": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
     "attention_dropout": 0.0,
-    "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,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
+    "hidden_act": "silu",
     "hidden_size": 1024,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 224,
+    "initializer_range": 0.02,
     "intermediate_size": 2816,
     "is_causal": false,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "aimv2",
-    "no_repeat_ngram_size": 0,
+    "is_native": false,
+    "mlp_bias": false,
+    "model_type": "aimv2_vision_model",
     "num_attention_heads": 8,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_channels": 3,
     "num_hidden_layers": 24,
     "num_queries": 1,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
     "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
     "projection_dropout": 0.0,
-    "pruned_heads": {},
     "qkv_bias": false,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
-    "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": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_bias": false
+    "use_bias": false,
+    "use_head": true
   }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c8b9fe2376ac8a5b7d15ea3175325447e819763c2372cf88596260bbcd9583
-size 1746752340
+oid sha256:4af6459935fb16d0bcaec436e7efdf69d3a235e89fe4b7206bbd22d284df4528
+size 1746763140

preprocessor_config.json

@@ -3,6 +3,10 @@
     "height": 224,
     "width": 224
   },
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
   "do_center_crop": true,
   "do_convert_rgb": true,
   "do_normalize": true,
@@ -13,15 +17,17 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "CLIPImageProcessor",
+  "image_processor_type": "CLIPImageProcessorFast",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
+  "input_data_format": null,
   "processor_class": "CLIPProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
   "size": {
     "shortest_edge": 224
   }

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<end_of_text>",
+  "pad_token": {
+    "content": "<end_of_text>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<end_of_text>",
     "lstrip": false,

tokenizer_config.json

@@ -21,9 +21,11 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<end_of_text>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 77,
   "pad_token": "<end_of_text>",
   "processor_class": "CLIPProcessor",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": "<end_of_text>"
+  "unk_token": "<end_of_text>",
+  "use_fast": true
 }