Upload model

config.json

@@ -4,10 +4,11 @@
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.1,
+  "attn_pdrop": 0.0,
   "bos_token_id": 50258,
-  "embd_pdrop": 0.1,
+  "embd_pdrop": 0.0,
   "eos_token_id": 50257,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -19,7 +20,7 @@
   "n_positions": 1024,
   "pad_token_id": 1,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
+  "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "sep_token_id": 50259,
@@ -28,8 +29,14 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "vocab_size": 50261
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 50258,
   "eos_token_id": 50257,
   "pad_token_id": 1,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.40.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee80539b4f28a9793fca19a939fc0d55877bb23fe160d1a73a499663f599617
+oid sha256:acc4d9006569ae7816690ee182288cf907e54466292798c85d5d08d79c235a3b
 size 497786496