Upload processor

README.md

@@ -1,11 +1,11 @@
 ---
 language:
 - en
+datasets:
+- liuhaotian/LLaVA-Instruct-150K
 pipeline_tag: image-to-text
 inference: false
 arxiv: 2304.08485
-datasets:
-- liuhaotian/LLaVA-Instruct-150K
 ---
 # BakLLaVA Model Card
 

preprocessor_config.json

@@ -1,4 +1,21 @@
 {
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "crop_size": {
     "height": 336,
     "width": 336

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "image_token": "<image>",
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}

tokenizer.json

@@ -37,7 +37,7 @@
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": false
+      "special": true
     },
     {
       "id": 32001,
@@ -152,6 +152,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -47,10 +48,10 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "padding_side": "left",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
+  "padding_side": "left",
   "processor_class": "LlavaProcessor",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,