parasail-ai
/

Qwen2.5-VL-72B-Instruct-quantized.w8a8

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions

zifeitong commited on Apr 17

Commit

74af1fe

·

verified ·

1 Parent(s): 63837e8

Update generation_config.json

Files changed (1) hide show

generation_config.json +4 -5

generation_config.json CHANGED Viewed

@@ -1,13 +1,12 @@
 {
   "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
     151643
   ],
-  "pad_token_id": 151643,
   "repetition_penalty": 1.05,
-  "top_k": 1,
-  "top_p": 0.001,
-  "transformers_version": "4.49.0.dev0"
-}

 {
   "bos_token_id": 151643,
+  "pad_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
     151645,
     151643
   ],
   "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "transformers_version": "4.49.0"
+}