added a pre trained nepali model with 86M params

nepali_pre_trained_model/config.json

@@ -0,0 +1,29 @@
+{
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "max_position_embeddings": 2048,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 2,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "transformers_version": "4.45.1",
+    "use_cache": true,
+    "vocab_size": 50000
+}

nepali_pre_trained_model/generation_config.json

@@ -0,0 +1,6 @@
+{
+    "_from_model_config": true,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "transformers_version": "4.45.1"
+}

nepali_pre_trained_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c389e584abe9845f13675e2fd4b1119c178d4070f9de74e4c737e2c1d0d229
+size 347490272