Upload of AutoGPTQ quantized model

config.json

@@ -21,7 +21,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 65024

gptq_model-4bit-128g.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7e8f87143610ac3921a1a99a8c002004ef4544c799b3de0f4fb912b6004a11
-size 4437779944
+oid sha256:236b4408720afb7d12a19f9b29c78019b092819aa28fa52599488c1494962300
+size 4437780008

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 2048,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {