Upload folder using huggingface_hub

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "MegatronGPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_megatron_gpt.MegatronGPTConfig",
+    "AutoModelForCausalLM": "modeling_megatron_gpt.MegatronGPTForCausalLM"
+  },
+  "bias": true,
+  "bos_token_id": 2,
+  "classifier_dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.01,
+  "intermediate_size": 10880,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "megatron_gpt",
+  "normalization": "layernorm1p",
+  "normalize_attention_scores": true,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "self_attention_relative_position_bias": true,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 56064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be72e7e2eca0bc35760a307f1ee166d396a658c54f6a19ea6ac0469ed178b18
+size 9970836963

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c87cbe98bb83d5b16c6e8ba81776b02fe4d0454f0398a669ba721c64f2f464
+size 950158711

pytorch_model.bin.index.json

@@ -0,0 +1,427 @@
+{
+  "metadata": {
+    "total_size": 10920847360
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.embed_in.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.0.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.1.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.10.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.11.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.12.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.13.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.14.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.15.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.16.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.17.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.18.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.19.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.2.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.20.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.21.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.22.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.23.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.24.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.25.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.26.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.27.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.28.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.29.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.3.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.30.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.30.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.31.self_attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "megatron_gpt.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.4.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.5.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.6.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.7.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.8.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "megatron_gpt.layers.9.self_attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}