Upload 9 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EleutherAI/gpt-neo-2.7B",
+  "_name_or_path": "./notes-nlp/gpt_neo_notes_pre",
   "activation_function": "gelu_new",
   "architectures": [
     "GPTNeoForCausalLM"
@@ -75,7 +75,7 @@
   },
   "tokenizer_class": "GPT2Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.27.2",
   "use_cache": true,
   "vocab_size": 50258,
   "window_size": 256

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.26.1"
+  "transformers_version": "4.27.2"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a663d237f36617806f9476302edb76be432a7c8bfb6e8d984211a09fa4bf73
-size 9996984169
+oid sha256:c8998bd59cf93fe14a866d72a521e63f67ed1b6727bc70496bb4e76fde1ceb84
+size 10106068835

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae9a578276b8a929c15e85357749068bbe10173f97fc8ddd79d86d78ccb682d
-size 742638515
+oid sha256:82cd5c78a022746235382eef2800dd18a0eb542f230d7abb6d17bead95c937a2
+size 633553991

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 10739458176
+    "total_size": 10622017664.0
   },
   "weight_map": {
     "transformer.h.0.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
@@ -346,8 +346,8 @@
     "transformer.h.29.ln_2.weight": "pytorch_model-00001-of-00002.bin",
     "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
     "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
     "transformer.h.3.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
     "transformer.h.3.attn.attention.k_proj.weight": "pytorch_model-00001-of-00002.bin",
     "transformer.h.3.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
@@ -363,15 +363,15 @@
     "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
     "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
     "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.30.attn.attention.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.attention.bias": "pytorch_model-00001-of-00002.bin",
     "transformer.h.30.attn.attention.k_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.30.attn.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.attn.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "transformer.h.30.attn.attention.out_proj.bias": "pytorch_model-00002-of-00002.bin",
     "transformer.h.30.attn.attention.out_proj.weight": "pytorch_model-00002-of-00002.bin",
     "transformer.h.30.attn.attention.q_proj.weight": "pytorch_model-00002-of-00002.bin",
     "transformer.h.30.attn.attention.v_proj.weight": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00001-of-00002.bin",
     "transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
     "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
     "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09b8b7058c768585bdbaa8b0f19a51a6261bdd64f78231fb559ff08715ea527
-size 3451
+oid sha256:f1366c71c60e969557fe221b2103dac00c9b4c2153c6081f264bda847cd37c95
+size 3515