add sharded checkpoint

.gitattributes

@@ -32,3 +32,12 @@ 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-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00009-of-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00005-of-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00007-of-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00009.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00006-of-00009.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stablelm-tuned-alpha-7b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 16,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf95fcdf7497c537e690de09a3fb18c4870cb5c0443c1b8c69757f8bf06c9a6
+size 3689415669

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0d2b6d12a86af05aba3feb2a9e407f1bb63466d3fa068ffda2cd409ec0c158
+size 3658082219

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee192d0b5eaa8080cca634c0f93d1b62330ef4d9e75dc213ed1fb0a973ef22af
+size 3658082219

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee595d747e10c66506f3a6aeeacf854f418025a2a48e9ce4115cef4a59934c33
+size 3658082219

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279bdd30901365ab5138af15b969afae0be42c73c61d798fc94bc86cfbd0e0e8
+size 3658082219

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f162dfca5745c27eda65edd4e09e5fcb7064a5fb5d63438d5950b55a26f94873
+size 3658082283

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834973322364a3c05276a8422fb5f7c9f36bb6684f153ebd1c741d88f3339fb2
+size 3658082283

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f537131b96cbe311845da6d71bba65946616dc2769f67fd2a770a15ce92d791
+size 3658082283

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8234cd52f71738d9d07f0bb06ccf9557933b2b6fca91cea4201f8506fc8f9dd8
+size 2447551184

pytorch_model.bin.index.json

@@ -0,0 +1,251 @@
+{
+  "metadata": {
+    "total_size": 31508579392.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_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|>"
+}