add sharded checkpoint

.gitattributes

@@ -32,3 +32,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00008-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00005-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00006-of-00008.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00007-of-00008.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "databricks/dolly-v2-7b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "custom_pipelines": {
+    "text-generation": {
+      "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
+      "pt": "AutoModelForCausalLM",
+      "tf": "TFAutoModelForCausalLM"
+    }
+  },
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50280
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1",
+  "use_cache": false
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e2562b97c49b3dc4282f7c18f647b1e25eb42b2024e01bf3a57b7ddd5b07b6
+size 3794210357

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530d4d98b0581c3e7bb46192a44e1cb811aa9f366739722dab93b14a9118cb84
+size 3780092209

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d361ba85367815f007b972f6770b8174706148ac7abc219e7b3f0476c807d9ad
+size 3981467953

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73afc181aaff7b15057159191317e587843aed1a632931bdbf94195d6bfca2c
+size 3847217457

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2546cdd01e9425217133b2f385e30414be572fc9e91d064c1be1c6c4e8cc0f
+size 3775879155

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b89e38a0bed49fffb673e878669d48fc2eea83658674a163c4444bb97bfd61
+size 3780092273

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd278a7b5dca4399a9776deb506d5660cbac584bcfc42b1c7cc7fbb78b881a65
+size 3775862707

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099da72429d4b3659331b424e6684b9065405a165c9688a808543b70ec6b4e63
+size 823788458

pytorch_model.bin.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 27441006720.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00008-of-00008.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.attention.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.attention.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.18.attention.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "gpt_neox.layers.19.attention.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.20.attention.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.attention.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.attention.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "gpt_neox.layers.23.attention.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.attention.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.attention.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.attention.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "gpt_neox.layers.30.attention.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.attention.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}