Upload model

README.md

@@ -11,10 +11,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # Nepali-GPT2-CausalLM
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [raygx/Nepali-GPT2-CausalLM](https://huggingface.co/raygx/Nepali-GPT2-CausalLM) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.6517
-- Validation Loss: 4.5987
+- Train Loss: 4.7022
+- Validation Loss: 4.6237
 - Epoch: 1
 
 ## Model description
@@ -41,8 +41,8 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 4.7603     | 4.6462          | 0     |
-| 4.6517     | 4.5987          | 1     |
+| 4.8141     | 4.6678          | 0     |
+| 4.7022     | 4.6237          | 1     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/kaggle/input/nepali-gpt2-model/gpt2NepaliCasualLM",
+  "_name_or_path": "raygx/Nepali-GPT2-CausalLM",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5427633d9bcf2c60a6610fc61f37b2659c9cc97f1ac171f2a450a8ba5a1f8233
+oid sha256:be9b84d76a37a4ce63144769fc23dac53785d3699829917a6a0e281fe29e835e
 size 497145936