💾 More intelligent!

config.json

@@ -14,7 +14,7 @@
   "n_embd": 1024,
   "n_head": 16,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 23,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -22,10 +22,14 @@
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
-  "summary_proj_to_hidden_size": true,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.51.1",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f0ddac0e77ba6d6bfe2be9d5c0373cdf956e0e7b07b31ef4423ef9f9e55038
-size 814689096
+oid sha256:2f2ea3cf4bfa44eb7e82bb789b8a67624399e6bad39aad579633e8e484033d33
+size 1368936712

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -17,8 +17,15 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 128,
   "model_max_length": 1024,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e2406db42b56f96a5b690237948e89d511c9d9e02b5d64c0ebcd289c4fc0d1
+size 5240