upload new config

model/config.json

@@ -1,53 +1,36 @@
 {
-  "_name_or_path": "EleutherAI/gpt-neo-125M",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPTNeoForCausalLM"
-  ],
-  "attention_dropout": 0,
-  "attention_layers": [
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local"
-  ],
-  "attention_types": [
-    [
-      [
-        "global",
-        "local"
-      ],
-      6
-    ]
+    "GPTJForCausalLM"
   ],
+  "attn_pdrop": 0.0,
   "bos_token_id": 50256,
-  "embed_dropout": 0,
+  "embd_pdrop": 0.0,
   "eos_token_id": 50256,
   "gradient_checkpointing": false,
-  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": null,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neo",
-  "num_heads": 12,
-  "num_layers": 12,
-  "resid_dropout": 0,
+  "model_type": "gptj",
+  "n_embd": 768,
+  "n_head": 16,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "rotary_dim": 64,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "transformers_version": "4.8.1",
+  "transformers_version": "4.10.0.dev0",
+  "tokenizer_class": "GPT2Tokenizer",
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "temperature": 1.0,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
   "use_cache": true,
-  "vocab_size": 50257,
-  "window_size": 256
-}
+  "vocab_size": 50400
+}