EZCon
/

Qwen2.5-VL-7B-Instruct-abliterated-4bit-mlx

Image-Text-to-Text

text-generation-inference

4-bit precision

Model card Files Files and versions

hermeschen-ezcon commited on 16 days ago

Commit

1cefdbf

·

verified ·

1 Parent(s): d327cb7

Upload folder using huggingface_hub

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -1184,7 +1184,7 @@
     "top_k": 50,
     "top_p": 1.0,
     "torchscript": false,
-    "transformers_version": "4.55.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,

     "top_k": 50,
     "top_p": 1.0,
     "torchscript": false,
+    "transformers_version": "4.56.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,