Upload model

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "gpt2NepaliCasualLM",
+  "_name_or_path": "raygx/GNePT",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPT2Model"
+    "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 0,
+  "bos_token_id": 1,
   "embd_pdrop": 0.1,
-  "eos_token_id": 0,
+  "eos_token_id": 2,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -17,7 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 50000,
+  "pad_token_id": 3,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -35,5 +35,5 @@
   },
   "transformers_version": "4.29.2",
   "use_cache": true,
-  "vocab_size": 50002
+  "vocab_size": 50000
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.29.2"
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818cd02ff2b2dfe59e41700dc93c04d72e7aaa9e258c0bf38581009c669d8e5e
-size 497152080
+oid sha256:f76404ce291f094200fb43ae939e9eeb919ba1e094b69cd104a62c44011c43f0
+size 497145936