Upload GPTNeoXForCausalLM

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1c437f3a950aec3e499b154dd98318910bc4351e440faa49fc46972315cfac
+size 131200

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a776242872ef38a36350884a10b2432f81819bebbad0e9b2150b56ea50b9e58
+size 103524

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13499b81fb0ce8bceeec62f8ff94080e4d7236abd5b38210e8f197c95e8040be
+size 39040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbcb66b7447f084554dce66f57d6513a78fc7781f2faba9d3bf194729bfaee6
+size 131192

model.safetensors.index.json

@@ -0,0 +1,71 @@
+{
+  "metadata": {
+    "total_size": 398180
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00004-of-00004.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00004.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors"
+  }
+}