Upload processor

preprocessor_config.json

@@ -1,18 +1,5 @@
 {
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
+  "do_convert_rgb": null,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
@@ -21,13 +8,13 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "CLIPImageProcessor",
+  "image_processor_type": "SiglipImageProcessor",
   "image_std": [
     0.5,
     0.5,
     0.5
   ],
-  "processor_class": "LlavaProcessor",
+  "processor_class": "SiglipProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {

special_tokens_map.json

@@ -1,20 +1,23 @@
 {
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
   "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
+    "content": "</s>",
+    "lstrip": true,
     "normalized": false,
-    "rstrip": false,
+    "rstrip": true,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
+    "content": "</s>",
+    "lstrip": true,
     "normalized": false,
-    "rstrip": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
     "single_word": false
   }
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5036bed065526c3c212dfbe288752391797c4bb1a284aa18c9a0b23fcaf8ec
+size 798330

tokenizer_config.json

@@ -1,52 +1,33 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151646": {
-      "content": "<image>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "model_input_names": [
+    "input_ids"
   ],
-  "bos_token": null,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "model_max_length": 64,
+  "pad_token": "</s>",
+  "processor_class": "SiglipProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SiglipTokenizer",
+  "unk_token": "<unk>"
 }