Making processor + model match.

config.json

@@ -0,0 +1,294 @@
+{
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 64,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 5,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.11.0.dev0",
+    "use_bfloat16": false,
+    "vocab_size": 99
+  },
+  "text_config_dict": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 5,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.11.0.dev0",
+    "use_bfloat16": false,
+    "vocab_size": 99
+  },
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 5,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 2,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.11.0.dev0",
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 5,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 2,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.11.0.dev0",
+    "use_bfloat16": false
+  },
+  "vocab_size": 1000
+}

merges.txt

@@ -0,0 +1,647 @@
+#version: 0.2 - Trained by `huggingface/tokenizers`
+Ġ t
+Ġt h
+Ġ a
+Ġth e</w>
+i n
+Ġ o
+Ġ ,</w>
+Ġ s
+e d</w>
+Ġ w
+e r
+Ġ .</w>
+Ġ i
+r e
+Ġ c
+n d</w>
+Ġ f
+Ġ b
+a t
+Ġo f</w>
+e r</w>
+e n
+a r
+o r
+i t
+Ġ p
+Ġ h
+Ġa nd</w>
+o n
+in g</w>
+a n
+r o
+Ġ m
+Ġ d
+e s</w>
+Ġi n</w>
+o n</w>
+Ġt o</w>
+o u
+i s
+Ġ a</w>
+i c
+Ġ T
+a l
+Ġ l
+Ġ =</w>
+Ġ re
+Ġ "</w>
+e s
+Ġ S
+a s</w>
+a l</w>
+i l
+e l
+i on</w>
+Ġ A
+Ġ C
+Ġ 1
+Ġ Ċ</w>
+u r
+ĠT h
+Ġ n
+a s
+Ġ @
+e c
+o m
+a c
+Ġ e
+Ġw as</w>
+Ġ M
+o r</w>
+a n</w>
+a m
+e n</w>
+o l
+Ġ in
+Ġ g
+Ġ '</w>
+Ġ B
+l y</w>
+a t</w>
+i v
+t s</w>
+ĠTh e</w>
+u s
+- @</w>
+Ġ@ -@</w>
+i s</w>
+Ġ I
+Ġw h
+i g
+Ġ H
+Ġs t
+o s
+u n
+t h
+Ġ P
+Ġw it
+Ġth at</w>
+i r
+Ġa s</w>
+e m
+Ġo n</w>
+r a
+Ġf or</w>
+Ġ R
+e t
+o w
+Ġ 2
+i d
+Ġ D
+l e</w>
+Ġwit h</w>
+l a
+en t</w>
+i m
+Ġ F
+e a
+i on
+Ġb y</w>
+Ġ )</w>
+Ġ (</w>
+Ġa l
+Ġc on
+en t
+Ġ W
+Ġi s</w>
+er e</w>
+Ġ G
+Ġ N
+Ġ L
+Ġh a
+er s</w>
+r i
+t h</w>
+t ed</w>
+u c
+Ġ J
+Ġ1 9
+e v
+u l
+Ġ v
+c e</w>
+at ion</w>
+ro m</w>
+Ġb e
+Ġ E
+i n</w>
+Ġth e
+Ġf rom</w>
+Ġ O
+t er</w>
+Ġp ro
+Ġa r
+a d
+Ġc om
+i c</w>
+a g
+Ġh is</w>
+Ġs h
+Ġa t</w>
+o v
+i es</w>
+o o
+p p
+s t
+c h
+Ġ r
+Ġ2 0
+a y</w>
+i f
+Ġw ere</w>
+Ġc h
+u t</w>
+s t</w>
+u t
+d s</w>
+o p
+u m
+Ġi t</w>
+o c
+t er
+l e
+ig h
+u d
+Ġe x
+ion s</w>
+at e</w>
+it y</w>
+at ed</w>
+Ġ un
+e p
+q u
+Ġn o
+Ġ K
+iv e</w>
+is t
+Ġo n
+am e</w>
+ou n
+i r</w>
+a b
+Ġ â
+in g
+Ġh e</w>
+l d</w>
+u g
+ic h</w>
+Ġa n</w>
+e d
+Ġ k
+Ġâ Ģ
+Ġha d</w>
+v e</w>
+a in
+Ġs e
+t ion</w>
+or e</w>
+re s
+Ġwh ich</w>
+ĠI n</w>
+o d
+th er</w>
+a k
+Ġs p
+a r</w>
+Ġ y
+ĠC h
+on g</w>
+Ġa c
+es t</w>
+Ġ U
+a p
+f f
+al ly</w>
+r it
+ĠS t
+u b
+g e</w>
+b er</w>
+e t</w>
+Ġb e</w>
+e ar
+Ġre c
+er s
+Ġf ir
+o t
+Ġar e</w>
+Ġa n
+c h</w>
+o g
+i a</w>
+es t
+in e</w>
+il l
+an d
+e l</w>
+ar y</w>
+e w</w>
+i d</w>
+Ġf or
+Ġ ;</w>
+Ġcom p
+Ġ V
+Ġin c
+t r
+Ġ20 0
+Ġthe ir</w>
+u s</w>
+Ġb ut</w>
+r an
+ic al</w>
+Ġfir st</w>
+Ġd e
+Ġin t
+Ġ ro
+s o</w>
+ĠâĢ ĵ</w>
+Ġno t</w>
+d ing</w>
+f ter</w>
+ur e</w>
+Ġp ar
+Ġ :</w>
+i an</w>
+Ġt w
+ou ld</w>
+Ġal so</w>
+Ġi ts</w>
+Ġw or
+u m</w>
+Ġo r</w>
+os t</w>
+0 0</w>
+ou r
+ar d</w>
+Ġre s
+m p
+u e</w>
+Ġa b
+is h</w>
+Ġcon t
+Ġa d
+ow n</w>
+al l</w>
+ou g
+Ġh er</w>
+as t</w>
+Ġ en
+om e</w>
+al l
+d ed</w>
+o w</w>
+Ġha ve</w>
+Ġ us
+ea r</w>
+ac k</w>
+d uc
+i al</w>
+s s
+en ts</w>
+a in</w>
+t ing</w>
+Ġon e</w>
+es s
+Ġh as</w>
+igh t</w>
+a v
+Ġe v
+ou t</w>
+a y
+en ce</w>
+Ġbe en</w>
+e w
+Ġtw o</w>
+Ġc l
+d er</w>
+im e</w>
+k s</w>
+es s</w>
+is h
+. @</w>
+Ġ@ .@</w>
+Ġp la
+Ġp l
+Ġo r
+u p</w>
+m ent</w>
+ur ing</w>
+ol l
+ĠI n
+Ġth is</w>
+Ġb ec
+Ġcom m
+Ġd is
+at er</w>
+ag e</w>
+Ġa pp
+ou s</w>
+e y</w>
+i l</w>
+p er
+ĠA l
+ion al</w>
+l ud
+el y</w>
+t t
+il e</w>
+i z
+Ġ j
+Ġwh o</w>
+Ġa g
+i b
+Ġthe y</w>
+f or
+Ġo v
+at h
+e g
+Ġs c
+i p
+Ġ20 1
+Ġ 3
+Ġp er
+or y</w>
+Ġd es
+id e</w>
+Ġs er
+s e</w>
+ĠH e</w>
+la nd</w>
+at ions</w>
+r ic
+i t</w>
+re s</w>
+er ed</w>
+Ġp re
+ĠS h
+an ce</w>
+or t</w>
+an t</w>
+, @</w>
+Ġ@ ,@</w>
+el l</w>
+Ġ Y
+n ed</w>
+el l
+it e</w>
+Ġinc lud
+Ġre p
+Ġa fter</w>
+Ġs uc
+re e</w>
+an y</w>
+i m</w>
+or t
+Ġ1 8
+Ġs u
+ad e</w>
+ou r</w>
+ĠU n
+ĠI t</w>
+i k
+ĠM ar
+em ber</w>
+Ġ 1</w>
+e en</w>
+a nd</w>
+Ġs ec
+ic e</w>
+Ġt ime</w>
+ĠA n
+Ġint o</w>
+Ġf in
+Ġo ther</w>
+Ġa tt
+il l</w>
+re n
+ac h
+as s
+er al</w>
+es e</w>
+s h
+al s</w>
+it ion</w>
+oug h</w>
+l es</w>
+am p
+Ġw ould</w>
+Ġm ore</w>
+ro ug
+ri b
+er y</w>
+ac e</w>
+Ġ A</w>
+Ġpla y
+it ed</w>
+k ed</w>
+is t</w>
+i ed</w>
+Ġ 2</w>
+as ed</w>
+ing s</w>
+an g
+a m</w>
+i p</w>
+Ġb o
+ab le</w>
+t y</w>
+Ġch ar
+Ġc ent
+et w
+at es</w>
+ro p
+Ġ I</w>
+u nd</w>
+ĠA m
+c es</w>
+o in
+Ġin ter
+u p
+c t
+on e</w>
+Ġt ra
+an t
+ec t
+Ġal l</w>
+e f
+Ġcon s
+ub l
+n ing</w>
+an s</w>
+Ġf e
+us t</w>
+Ġ 0
+Ġre m
+as e</w>
+on g
+Ġwh en</w>
+e b
+ĠW h
+Ġe ar
+ev er</w>
+Ġov er</w>
+Ġk n
+a us
+Ġp os
+a d</w>
+er m
+Ġsh e</w>
+Ġ ra
+Ġd uring</w>
+as on</w>
+v i
+Ġex p
+Ġl ea
+Ġ el
+Ġ 4
+Ġon ly</w>
+o nd</w>
+Ġd ec
+Ġac c
+Ġo ff
+is s
+Ġf l
+ĠE n
+o t</w>
+en s
+os e</w>
+ak e</w>
+o m</w>
+Ġs ev
+ac h</w>
+etw een</w>
+er n
+Ġ 3</w>
+Ġp r
+Ġg ro
+r uc
+Ġd i
+Ġ19 9
+ĠA r
+Ġg ame</w>
+Ġh im</w>
+oo k</w>
+Ġ up</w>
+Ġab out</w>
+Ġre l
+for m
+Ġth ree</w>
+at t
+ĠC om
+Ġs a
+ear s</w>
+Ġ 5
+r y</w>
+Ġi mp
+Ġm ost</w>
+f er
+Ġp res
+Ġf il
+Ġb etween</w>
+Ġbe g
+p h
+or s</w>
+Ġth an</w>
+Ġrec or
+o b
+er ic
+at ing</w>
+Ġth roug
+k ing</w>
+Ġo ut</w>
+Ġn um
+oo d</w>
+oll ow
+ac t
+u il
+Ġc re
+ol og
+at ional</w>
+Ġpro duc
+Ġwh ile</w>
+Ġl ater</w>
+Ġw rit
+e x
+Ġst ar
+Ġsp ec
+e e
+ish ed</w>
+Ġre g
+is ion</w>
+ou th</w>
+Ġre le
+Ġa ss
+Ġse ason</w>
+Ġm ade</w>
+il y</w>
+r u
+o y
+t ur
+t e</w>
+Ġ qu
+Ġm ov
+ur y</w>
+ĠAm eric
+em ent</w>
+c c
+ou nd</w>
+Ġl ar
+Ġfor m
+ec t</w>
+Ġde f
+Ġm us
+ĠP ar
+Ġm e
+Ġs ub
+w ay</w>
+o p</w>
+o h
+el d</w>
+i e</w>
+em p
+am es</w>
+er n</w>
+Ġn or
+iv ed</w>
+ev el
+Ġsuc h</w>
+ar ds</w>
+Ġin d
+ik e</w>
+Ġg en
+er t
+Ġy ear</w>
+Ġus ed</w>
+Ġn ew</w>
+Ġ 5</w>
+Ġal b
+s p
+y p
+Ġwit h
+Ġwh ere</w>
+ic s</w>
+ĠTh is</w>
+Ġthe m</w>
+w n</w>

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+    "crop_size": 224,
+    "do_center_crop": true,
+    "do_normalize": true,
+    "do_resize": true,
+    "feature_extractor_type": "CLIPFeatureExtractor",
+    "image_mean": [0.48145466, 0.4578275, 0.40821073],
+    "image_std": [0.26862954, 0.26130258, 0.27577711],
+    "resample": 3,
+    "size": 30
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "do_lower_case": true, "name_or_path": "openai/clip-vit-base-patch32", "model_max_length": 77, "special_tokens_map_file": "/home/lysandre/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5", "tokenizer_class": "CLIPTokenizer"}