add transformers gptq support (#963)

Proposal to fix
https://github.com/huggingface/text-generation-inference/issues/962

server/text_generation_server/utils/weights.py

@@ -223,6 +223,17 @@ class Weights:
         return bits, groupsize
 
     def _set_gptq_params(self, model_id):
+        filename = "config.json"
+        try:
+            if os.path.exists(os.path.join(model_id, filename)):
+                filename = os.path.join(model_id, filename)
+            else:
+                filename = hf_hub_download(model_id, filename=filename)
+            with open(filename, "r") as f:
+                data = json.load(f)
+            self.gptq_bits = data["quantization_config"]["bits"]
+            self.gptq_groupsize = data["quantization_config"]["group_size"]
+        except Exception:
             filename = "quantize_config.json"
             try:
                 if os.path.exists(os.path.join(model_id, filename)):