Upload OPTForCausalLM

config.json

@@ -33,6 +33,8 @@
             "_data": "float8_e4m3fn",
             "_type": "torch.dtype"
           },
+          "activation_value_lb": null,
+          "activation_value_ub": null,
           "granularity": [
             {
               "_data": {},
@@ -45,6 +47,10 @@
               "_version": 1
             }
           ],
+          "kernel_preference": {
+            "_data": "AUTO",
+            "_type": "KernelPreference"
+          },
           "mm_config": {
             "_data": {
               "emulate": false,
@@ -54,10 +60,6 @@
             "_type": "Float8MMConfig",
             "_version": 1
           },
-          "packing_format": [
-            "plain",
-            "plain"
-          ],
           "set_inductor_config": true,
           "weight_dtype": {
             "_data": "float8_e4m3fn",
@@ -65,14 +67,14 @@
           }
         },
         "_type": "Float8DynamicActivationFloat8WeightConfig",
-        "_version": 1
+        "_version": 2
       }
     },
     "quant_type_kwargs": {},
     "untie_embedding_weights": false
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.53.0",
+  "transformers_version": "4.55.2",
   "use_cache": true,
   "vocab_size": 50272,
   "word_embed_proj_dim": 768

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.53.0"
+  "transformers_version": "4.55.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6b28caf856b841061a3cc5951e01ca58c3c131e9591a6ef19c469c50c9e4f1
-size 165982035
+oid sha256:0041f4c0acffec7140506f9d6c3600a6b23fae40d703d21a6ee574927c61e163
+size 165976723