Upload 6 files

config.json

@@ -1,42 +1,26 @@
 {
-  "_name_or_path": "/finetune-data/models/EleutherAI/gpt-j-6B",
-  "activation_function": "gelu_new",
+  "_name_or_path": "/finetune-data/models/rexwang8/py2.8b",
   "architectures": [
-    "GPTJForCausalLM"
+    "GPTNeoXForCausalLM"
   ],
-  "attn_pdrop": 0.0,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 50256,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
   "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gptj",
-  "n_embd": 4096,
-  "n_head": 16,
-  "n_inner": null,
-  "n_layer": 28,
-  "n_positions": 2048,
-  "resid_pdrop": 0.0,
-  "rotary": true,
-  "rotary_dim": 64,
-  "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,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50,
-      "temperature": 1.0
-    }
-  },
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "tokenizer_class": "GPT2Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.17.0",
+  "transformers_version": "4.25.1",
   "use_cache": false,
-  "vocab_size": 50257
+  "use_parallel_residual": true,
+  "vocab_size": 50277
 }

special_tokens_map.json

@@ -1 +1,5 @@
-{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -1 +1,11 @@
-{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "/finetune-data/models/EleutherAI/gpt-j-6B", "pad_token": "", "tokenizer_class": "GPT2Tokenizer"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "/finetune-data/models/rexwang8/py2.8b",
+  "pad_token": "",
+  "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae3f9d5e4341f5b96bbfe8cb08c5a1cae7489948754dc62253230639d1be9da
-size 4399
+oid sha256:9d27d88d5adabc9f21d47fa0601324a7793fbd073f98458433ef4ba58025b565
+size 4795