Upload GPTNeoXForCausalLM

config.json

@@ -1,32 +1,29 @@
 {
-  "_name_or_path": "/home/bts/pretrain-subnet-2/local-models/training/2024-01-05_07-22-07",
-  "activation_function": "gelu_new",
+  "_name_or_path": "/dev/shm/checkpoints-pythia/checkpoint-500",
   "architectures": [
-    "GPT2LMHeadModel"
+    "GPTNeoXForCausalLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_embd": 760,
-  "n_head": 10,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 15,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "use_parallel_residual": true,
+  "vocab_size": 50304
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "transformers_version": "4.34.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c743420f48d8e666c7baff3a9e22270c7a7bfffac9e3fa402ed52a7ad4ee5c
-size 489087136
+oid sha256:b60cfc2abed97a1fec53b9c9940ae1924433d64b624c98b017db17e561243f12
+size 734369568