Initial GPTQ model commit

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "user_token_id": 195,
+  "assistant_token_id": 196,
+  "max_new_tokens": 2048,
+  "temperature": 0.3,
+  "top_k": 5,
+  "top_p": 0.85,
+  "repetition_penalty": 1.05,
+  "do_sample": true,
+  "transformers_version": "4.29.2"
+}