Upload of AutoGPTQ quantized model

config.json

@@ -21,7 +21,7 @@
   "rope_scaling": null,
   "rope_theta": 500000,
   "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 sha256:5476dcd83439ca695c3fc0102ea87bd2fc61035ac4b581446f0feb9209149e18
-size 4437779944
+oid sha256:4dbb1e500b57e5939a4120595d1a37d53ba23b3af3ba13b0f85c236a664d001f
+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": [
     {