Upload model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/workspace/new/pretraining/local-models/training/2024-01-07_17-24-23",
+  "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-01_15-15-06",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -11,10 +11,11 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
+  "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 11,
+  "n_layer": 20,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.0,
@@ -25,6 +26,12 @@
   "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": "4.34.1",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f303e97fe68bde230c0fbb9144cb4b795000cb9b101db908c0788a88e6cab98
-size 469421488
+oid sha256:86fbefd2dab45a47244c54a712981e73d5d489a38e8c1312a08683921922da66
+size 724595976