added gptq config

huggingface · Nov 27, 2023 · 14a32a6 · 14a32a6
1 parent 6b6513c
commit 14a32a6
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 1 deletion.
diff --git a/examples/running-llamas/configs/fp16+gptq.yaml b/examples/running-llamas/configs/fp16+gptq.yaml
@@ -0,0 +1,10 @@
+defaults:
+  - _base_
+  - _self_
+
+experiment_name: fp16+gptq
+
+backend:
+  quantization_scheme: gptq
+  quantization_config:
+    bits: 4
diff --git a/optimum_benchmark/backends/pytorch/config.py b/optimum_benchmark/backends/pytorch/config.py
@@ -18,7 +18,7 @@
 TORCH_DTYPES = ["bfloat16", "float16", "float32", "auto"]
 
 QUANTIZATION_CONFIGS = {
-    "gptq": {"dataset": ["lorem ipsum dolor sit amet consectetur"]},
+    "gptq": {},
     "bnb": {"llm_int8_threshold": 0.0},
     "awq": {},
 }