Upload model

config.json

@@ -1,37 +1,30 @@
 {
-  "_name_or_path": "/root/config.json",
-  "activation_function": "silu",
+  "_name_or_path": "/root/pretraining/local-models/training/2024-01-31_17-27-13",
+  "activation_function": "gelu_new",
   "architectures": [
-    "GPT2Model"
+    "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.0,
+  "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "embd_pdrop": 0.0,
+  "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
-  "n_inner": 3072,
+  "n_embd": 760,
+  "n_head": 10,
+  "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.0,
+  "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
-  "summary_first_dropout": 0.0,
+  "summary_first_dropout": 0.1,
   "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,

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.34.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3670784cb9c904295970f1a529e86737351a89501eb1a857416c9d173c1ca8d
-size 713974864
+oid sha256:66f1ae502accd10313c5755fbfb0f004f748ed12491f907aee0318926f945f40
+size 489087136