Upload GPTNeoXForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./pythia-delphi-suboptimal",
+  "_name_or_path": "jtatman/pythia-delphi-suboptimal",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -27,7 +27,7 @@
   "rotary_pct": 0.5,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.42.3",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50281

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 0,
   "eos_token_id": 0,
   "pad_token_id": 0,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.42.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f772897121d3a5f0c9be023dee58f6e036851129d9a60734d152361af3cf176c
-size 4076812760
+oid sha256:c10fabe7cff8e9f31da5ef1b73d8c999007f3561bfc2c933af333402a75d4b08
+size 4064201824

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5724416000
+    "total_size": 5711806464
   },
   "weight_map": {
     "embed_out.weight": "model-00002-of-00002.safetensors",
@@ -30,18 +30,6 @@
     "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
     "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
     "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
-    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
   }
 }