Upload model

README.md

@@ -1,18 +1,20 @@
 ---
-license: apache-2.0
+license: mit
 tags:
-- management
-- text generation
+- generated_from_keras_callback
 model-index:
 - name: ManaGPT-1010
   results: []
-language:
-- en
 ---
 
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
 # ManaGPT-1010
-<img style="float:right; margin-right:30px" src="https://huggingface.co/NeuraXenetica/ManaGPT-1010/resolve/main/ManaGPT_logo_01.png" width="150" height="150">
-This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on a custom dataset.
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+
 
 ## Model description
 
@@ -43,4 +45,4 @@ The following hyperparameters were used during training:
 - Transformers 4.27.1
 - TensorFlow 2.11.0
 - Datasets 2.10.1
-- Tokenizers 0.13.2
+- Tokenizers 0.13.2

config.json

@@ -1,6 +1,5 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -10,13 +9,7 @@
   "do_sample": true,
   "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,
   "max_length": 50,
   "model_type": "gpt2",
@@ -24,7 +17,7 @@
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 6,
+  "n_layer": 12,
   "n_positions": 1024,
   "pad_token_id": 50256,
   "reorder_and_upcast_attn": false,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928fcd99565456294c904d0ced5e0c9e81871df1a9511bbfa9a0e2da47fd62a5
-size 327745472
+oid sha256:cb46ed853ac5704b211c087abcd299d904b9f69b2b959d84e6a00e17a546b931
+size 497935440