Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 image_encoder.axmodel filter=lfs diff=lfs merge=lfs -text
 text_encoder.axmodel filter=lfs diff=lfs merge=lfs -text
+jina-clip-v2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

jina-clip-v2/config.json

@@ -0,0 +1,70 @@
+{
+    "add_projections": false,
+    "architectures": [
+        "JinaCLIPModel"
+    ],
+    "auto_map": {
+        "AutoConfig": "jinaai/jina-clip-implementation--configuration_clip.JinaCLIPConfig",
+        "AutoModel": "jinaai/jina-clip-implementation--modeling_clip.JinaCLIPModel"
+    },
+    "initializer_factor": 1.0,
+    "logit_scale_init_value": 2.6592,
+    "matryoshka_dimensions": [32, 64, 128, 256, 512, 768, 1024],
+    "model_type": "jina_clip",
+    "projection_dim": 1024,
+    "text_config": {
+        "default_instruction_task": null,
+        "default_lora_task": "retrieval.query",
+        "embed_dim": 1024,
+        "hf_model_config_kwargs": {
+            "load_trained_adapters": false,
+            "lora_adaptations": [
+                "retrieval.query"
+            ],
+            "lora_alpha": 4,
+            "lora_dropout_p": 0.0,
+            "lora_main_params_trainable": false,
+            "lora_rank": 4,
+            "task_instructions": {
+                "retrieval.query": "Represent the query for retrieving evidence documents: "
+            },
+            "use_flash_attn": true
+        },
+        "hf_model_name_or_path": "jinaai/jina-embeddings-v3",
+        "model_type": "jina_clip_text",
+        "pooler_type": "mean_pooler",
+        "proj_bias": false,
+        "proj_type": null
+    },
+    "torch_dtype": "bfloat16",
+    "transformers.js_config": {
+        "use_external_data_format": {
+            "model.onnx": true
+        }
+    },
+    "truncate_dim": null,
+    "use_text_flash_attn": null,
+    "use_vision_xformers": null,
+    "vision_config": {
+        "embed_dim": 1024,
+        "fused_layer_norm": false,
+        "head_width": 64,
+        "image_size": 512,
+        "intp_freq": true,
+        "layers": 24,
+        "ls_init_value": null,
+        "mlp_ratio": 2.6667,
+        "model_type": "jina_clip_vision",
+        "naive_swiglu": true,
+        "patch_dropout": 0.1,
+        "patch_size": 14,
+        "post_norm": false,
+        "proj_type": null,
+        "pt_hw_seq_len": 16,
+        "qkv_bias": true,
+        "rope_embeddings": true,
+        "subln": true,
+        "width": 1024,
+        "x_attention": true
+    }
+}

jina-clip-v2/config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.0",
+    "transformers": "4.46.2",
+    "pytorch": "2.2.2"
+  },
+  "prompts":{
+    "retrieval.query":"Represent the query for retrieving evidence documents: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

jina-clip-v2/modules.json

@@ -0,0 +1,14 @@
+[
+    {
+        "idx": 0,
+        "name": "transformer",
+        "path": "",
+        "type": "custom_st.Transformer"
+    },
+    {
+        "idx": 1,
+        "name": "normalizer",
+        "path": "1_Normalize",
+        "type": "sentence_transformers.models.Normalize"
+    }
+]

jina-clip-v2/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+    "auto_map": {
+        "AutoImageProcessor": "jinaai/jina-clip-implementation--processing_clip.JinaCLIPImageProcessor",
+        "AutoProcessor": "jinaai/jina-clip-implementation--processing_clip.JinaCLIPProcessor"
+    },
+    "fill_color": 0,
+    "image_processor_type": "JinaCLIPImageProcessor",
+    "interpolation": "bicubic",
+    "mean": [
+        0.48145466,
+        0.4578275,
+        0.40821073
+    ],
+    "processor_class": "JinaCLIPProcessor",
+    "resize_mode": "shortest",
+    "size": 512,
+    "std": [
+        0.26862954,
+        0.26130258,
+        0.27577711
+    ]
+}

jina-clip-v2/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

jina-clip-v2/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6601c4120779a1a3863897ba332fe3481d548e363bec2c91eba10ef8640a5e93
+size 17082997

jina-clip-v2/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 8194,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}