Finally working: Redundant TEXT model for HF inference

This is a copy of the TEXT model (latest, as of 21-SEPT-2024) you can use with Transformers.

config.json

@@ -1,171 +1,30 @@
-{
- "_name_or_path": "CLIP-GmP-ViT-L-14",
- "architectures": [
- "CLIPModel"
- ],
- "initializer_factor": 1.0,
- "logit_scale_init_value": 4.6052,
- "model_type": "clip",
- "projection_dim": 768,
- "text_config": {
- "_name_or_path": "",
- "add_cross_attention": false,
- "architectures": null,
- "attention_dropout": 0.0,
- "bad_words_ids": 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,
- "dropout": 0.0,
- "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,
- "hidden_act": "quick_gelu",
- "hidden_size": 768,
- "id2label": {
- "0": "LABEL_0",
- "1": "LABEL_1"
- },
- "initializer_factor": 1.0,
- "initializer_range": 0.02,
- "intermediate_size": 3072,
- "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": 77,
- "min_length": 0,
- "model_type": "clip_text_model",
- "no_repeat_ngram_size": 0,
- "num_attention_heads": 12,
- "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": 1,
- "prefix": null,
- "problem_type": null,
- "projection_dim" : 768,
- "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": "4.44.2",
- "use_bfloat16": false,
- "vocab_size": 49408
- },
- "text_config_dict": {
- "hidden_size": 768,
- "intermediate_size": 3072,
- "num_attention_heads": 12,
- "num_hidden_layers": 12,
- "projection_dim": 768
- },
- "torch_dtype": "float32",
- "transformers_version": "4.44.2",
- "vision_config": {
- "_name_or_path": "",
- "add_cross_attention": false,
- "architectures": null,
- "attention_dropout": 0.0,
- "bad_words_ids": 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,
- "dropout": 0.0,
- "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,
- "hidden_act": "quick_gelu",
- "hidden_size": 1024,
- "id2label": {
- "0": "LABEL_0",
- "1": "LABEL_1"
- },
- "image_size": 224,
- "initializer_factor": 1.0,
- "initializer_range": 0.02,
- "intermediate_size": 4096,
- "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": 16,
- "num_beam_groups": 1,
- "num_beams": 1,
- "num_hidden_layers": 24,
- "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_dim" : 768,
- "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": "4.44.2",
- "use_bfloat16": false
- },
- "vision_config_dict": {
- "hidden_size": 1024,
- "intermediate_size": 4096,
- "num_attention_heads": 16,
- "num_hidden_layers": 24,
- "patch_size": 14,
- "projection_dim": 768
- }
-}
+{
+ "_name_or_path": "CLIP-GmP-ViT-L-14/",
+ "architectures": [
+ "CLIPModel"
+ ],
+ "initializer_factor": 1.0,
+ "logit_scale_init_value": 4.6052,
+ "model_type": "clip",
+ "projection_dim": 768,
+ "text_config": {
+ "dropout": 0.0,
+ "hidden_size": 768,
+ "intermediate_size": 3072,
+ "model_type": "clip_text_model",
+ "num_attention_heads": 12,
+ "projection_dim": 768
+ },
+ "torch_dtype": "float32",
+ "transformers_version": "4.44.2",
+ "vision_config": {
+ "dropout": 0.0,
+ "hidden_size": 1024,
+ "intermediate_size": 4096,
+ "model_type": "clip_vision_model",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "patch_size": 14,
+ "projection_dim": 768
+ }
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac763df1ffb38528dfa598b24a08d42a877f0af9edc7da0fe61a29add1e5e897
-size 1710540580
+oid sha256:0b820c4ef9a06ed7a5872b064405a69e26ebba5f524c92263b9bec1692a71bd7
+size 1710537716