andrewhinh
/

qwen2-vl-7b-instruct-lora-dpo-merged

Image-Text-to-Text

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

andrewhinh commited on about 6 hours ago

Commit

044c904

·

verified ·

1 Parent(s): 22bc7b7

Upload processor

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -134,7 +134,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "processor_class": "Qwen2VLProcessor",

   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "processor_class": "Qwen2VLProcessor",