v6 re-export: legacy torch.onnx.export (opset 14) — fp32 + int8

config.json

@@ -1,5 +1,6 @@
 {
   "activation_function": "gelu_new",
+  "add_cross_attention": false,
   "architectures": [
     "GPT2LMHeadModel"
   ],
@@ -18,6 +19,7 @@
   "n_layer": 24,
   "n_positions": 1024,
   "n_special": 0,
+  "pad_token_id": null,
   "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -34,7 +36,8 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.57.6",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.57.6"
+  "transformers_version": "5.6.0.dev0"
 }

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db2f92413725d2f17be7af1fe4d2d11d0c8bc0636b988e7397fa9213fccac72
+size 1627259635

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c579c19995a99717ff077ce802bccd4a342395ab384290aacd17b986dac082
-size 357987215
+oid sha256:13216ddcad93106c7fcf967c35d75687ef8b3fdf8d9ae2c3c469a4cb1bff1dae
+size 409946473