Model save

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: openai-community/gpt2
+base_model: openai-community/gpt2-large
 tags:
 - trl
 - sft
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # digital-TA
 
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai-community/gpt2",
+  "_name_or_path": "openai-community/gpt2-large",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,10 +12,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1280,
+  "n_head": 20,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 36,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb33db464c71805ce33bf89dcf760f787a2d3aaf8eae5f9177d81818b4c6bf9a
-size 497774208
+oid sha256:5956dc6c118dd5bff923babb8a3f33a828a67675cfe8227e462f708c601245cb
+size 3096165928

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88e4fb2375d06ccbe0bc5249bedead2507f4daac32ce709863dd35d525a62dfc
+oid sha256:ee5c36a69700cdca36f1b61836e5242fe09d3e80188de12abd17af730e0c2a26
 size 4984