Fix transformers version (#156)

When running AWQ search foe Llama2 with transformers>=4.38.0, I find the bug below:
File "/×××/llm-awq/awq/quantize/auto_scale.py", line 134, in _search_module_scale
RuntimeError: The expanded size of the tensor (4608) must match the existing size (4096) at non-singleton dimension 3. Target sizes: [65, 32, 512, 4608]. Tensor sizes: [65, 1, 512, 4096]
But earlier versions of transformers would not happen this. So I set transformers==4.36.2.

pyproject.toml

@@ -15,7 +15,7 @@ classifiers = [
 dependencies = [
     "accelerate", "sentencepiece", "tokenizers>=0.12.1",
     "torch>=2.0.0", "torchvision", 
-    "transformers>=4.32.0", 
+    "transformers==4.36.2", 
     "lm_eval==0.3.0", "texttable",
     "toml", "attributedict",
     "protobuf",