Add b16 clip

config.json

@@ -1,4 +1,5 @@
 {
+  "_commit_hash": "40ec06f4e5e6642fcb394ba4211c01a75ec17d7c",
   "architectures": [
     "CLIPViPModel"
   ],
@@ -12,8 +13,10 @@
     "architectures": null,
     "attention_dropout": 0.0,
     "bad_words_ids": null,
+    "begin_suppress_tokens": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -21,6 +24,7 @@
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
@@ -57,15 +61,17 @@
     "pad_token_id": 1,
     "prefix": null,
     "problem_type": null,
-    "projection_dim" : 512,
+    "projection_dim": 512,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
     "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,
@@ -73,7 +79,8 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.12.0.dev0",
+    "transformers_version": "4.30.0.dev0",
+    "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
   },
@@ -87,8 +94,10 @@
     "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,
@@ -96,6 +105,7 @@
     "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,
@@ -117,7 +127,7 @@
     },
     "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
-    "logit_scale_init_value": 4.60,
+    "logit_scale_init_value": 4.6,
     "max_length": 20,
     "min_length": 0,
     "model_type": "clip_vip_vision_model",
@@ -125,6 +135,7 @@
     "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
+    "num_channels": 3,
     "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -134,16 +145,18 @@
     "patch_size": 16,
     "prefix": null,
     "problem_type": null,
-    "projection_dim" : 512,
+    "projection_dim": 512,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
     "sep_token_id": null,
+    "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
     "temporal_size": 12,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -151,10 +164,12 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.12.0.dev0",
-    "use_bfloat16": false
+    "transformers_version": "4.30.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_temporal_embed": true
   },
   "vision_config_dict": {
     "patch_size": 16
   }
-}
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05148d0605a6977d9ee1b48e282a78e48f1b9e8ec84f5f3d34735962496554c7
+size 598663509