Upload config.json with huggingface_hub

config.json

@@ -1,43 +1,27 @@
 {
   "activation_function": "gelu_new",
   "architectures": [
-    "GPTNeoForCausalLM"
-  ],
-  "attention_dropout": 0,
-  "attention_layers": ["global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global"],
-  "attention_types": [
-    [
-      [
-        "global"
-      ],
-      28
-    ]
+    "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": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": null,
-  "jax": true,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neo",
-  "num_heads": 16,
-  "num_layers": 28,
-  "resid_dropout": 0,
-  "rotary": true,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_layer": 28,
+  "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": "4.5.0.dev0",
-  "use_cache": true,
-  "vocab_size": 50400,
-  "window_size": 256,
+  "transformers_version": "4.10.0.dev0",
   "tokenizer_class": "GPT2Tokenizer",
   "task_specific_params": {
     "text-generation": {
@@ -45,5 +29,8 @@
       "temperature": 1.0,
       "max_length": 50
     }
-  }
+  },
+  "torch_dtype": "float16",
+  "use_cache": true,
+  "vocab_size": 50400
 }