Upload model

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "/pretraining/local-models/training/2024-01-04_13-54-42",
+  "_name_or_path": "/pretraining/Local-Distill",
+  "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,13 +9,20 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_embd": 760,
-  "n_head": 10,
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 6,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -25,6 +33,12 @@
   "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 sha256:534a8e0449e127d207d3472546eba38f804cc60e51875dea906a0c80e47aa5a9
-size 489087136
+oid sha256:721fa38acb2ba5d1ebdeed4bad3dcb32c0beeb2b924ecf544fffaa3b0bb65a66
+size 327657928