Upload final model

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "ParamBharatGenForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "config_parambharatgen.ParamBharatGenConfig",
+    "AutoModelForCausalLM": "modeling_parambharatgen.ParamBharatGenForCausalLM"
+  },
+  "bos_token_id": 2,
+  "custom_mlp_ratio": 3.5,
+  "dtype": "bfloat16",
+  "eos_token_id": 256001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.01,
+  "intermediate_size": 7168,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "parambharatgen",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 256002,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vocab_size": 256011
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545b23e7cf899531082ffe5d55907154e027ce5b0e923b21233b132c886e8ba2
+oid sha256:b42b8ef561adc419db65785ea688724e25d64f48e91e86877ff35d26c27c5ba3
 size 5721420784

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e25d938f6b6e7079164fe4ac0abf1b15c1d5d3f52336cde2eb648d428957543
+oid sha256:2a1fb3a0ee8ef2b160578cd2203efeb4061c8e30d8c1df0c4a7d90d87e7f1f92
 size 5265