Fix support for SGLang inference

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "architectures": [
-    "LlavaMistralForCausalLM"
+    "LlavaLlamaForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
@@ -49,7 +49,7 @@
   "mm_vision_select_layer": -2,
   "mm_vision_tower": "openai/clip-vit-large-patch14-336",
   "mm_vision_tower_lr": 2e-06,
-  "model_type": "llava_mistral",
+  "model_type": "llava",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 32001,
   "transformers_version": "4.36.2"
 }

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+	"crop_size": {
+	  "height": 336,
+	  "width": 336
+	},
+	"do_center_crop": true,
+	"do_convert_rgb": true,
+	"do_normalize": true,
+	"do_rescale": true,
+	"do_resize": true,
+	"image_mean": [
+	  0.48145466,
+	  0.4578275,
+	  0.40821073
+	],
+	"image_processor_type": "CLIPImageProcessor",
+	"image_std": [
+	  0.26862954,
+	  0.26130258,
+	  0.27577711
+	],
+	"processor_class": "LlavaProcessor",
+	"resample": 3,
+	"rescale_factor": 0.00392156862745098,
+	"size": {
+	  "shortest_edge": 336
+	}
+  }
+  

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<unk>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -29,6 +29,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32001,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -25,17 +25,33 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
   "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 4096,
-  "pad_token": "<unk>",
-  "padding_side": "left",
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",