tclf90
/

qwen2.5-72b-instruct-gptq-int4

Text Generation

4-bit precision

Model card Files Files and versions

tclf90 commited on Nov 4, 2024

Commit

ec4e725

·

verified ·

1 Parent(s): a658d7b

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -19,7 +19,7 @@
   "quantization_config": {
     "batch_size": 1,
     "bits": 4,
-    "block_name_to_quantize": null,
     "cache_block_outputs": true,
     "damp_percent": 0.1,
     "dataset": null,

   "quantization_config": {
     "batch_size": 1,
     "bits": 4,
+    "block_name_to_quantize": "model.layers",
     "cache_block_outputs": true,
     "damp_percent": 0.1,
     "dataset": null,