Upload model

README.md

@@ -6,12 +6,13 @@ model-index:
   results: []
 ---
 
-
+<!-- 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. -->
 
 # text_generation_bangla_model
 
-This model was trained from scratch on the Oscar dataset, Prothom Alo and bdnews24.com website news
-
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
 
 
 ## Model description
@@ -29,13 +30,6 @@ More information needed
 ## Training procedure
 
 ### Training hyperparameters
-Learning rate: 5e-5
-num_warmup_steps: 1000
-weight_decay_rate: 0.01
-batch_size: 8
-Trainable params: 124,439,808
-
-
 
 The following hyperparameters were used during training:
 - optimizer: None
@@ -47,7 +41,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.21.2
-- TensorFlow 2.8.2
-- Datasets 2.4.0
-- Tokenizers 0.12.1
+- Transformers 4.26.1
+- TensorFlow 2.11.0
+- Datasets 2.10.0
+- Tokenizers 0.13.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/text generation model",
+  "_name_or_path": "/content/drive/MyDrive/text generation model/pytorch model",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -34,7 +34,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.21.2",
+  "transformers_version": "4.26.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.26.1"
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc1fe88b1c197919d9ac369d11ae626f339b6f541b2f05ed9875b9824a3dea6
+oid sha256:d447109af3b01b776410a3ebc25c69f808d4efc3839016f4029574367cb9d3a3
 size 497935464