add model

config.json

@@ -1,28 +1,28 @@
 {
+  "_name_or_path": "opt-350m",
   "activation_dropout": 0.0,
-  "activation_function": "gelu",
+  "activation_function": "relu",
   "architectures": [
     "OPTModel"
   ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": true,
   "vocab_size": 50272,
-  "max_position_embeddings":2048,
-  "num_hidden_layers":24,
-  "num_attention_heads":16,
-  "ffn_dim":4096,
-  "layerdrop":0.0,
-  "d_model":1024,
-  "embed_dim":512,
-  "dropout":0.1,
-  "attention_dropout":0.0,
-  "init_std":0.02,
-  "scale_embedding":false,
-  "share_input_output_embed":true,
-  "use_cache":false,
-  "pad_token_id":1,
-  "bos_token_id":0,
-  "eos_token_id":2,
-  "decoder_start_token_id":2,
-  "forced_eos_token_id":2,
-  "output_projection":true,
-  "decoder_layernorm":false
+  "word_embed_proj_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866995abded477a0e8c7c05a492d607e97b5f168e02586f2bfbad23e50f763e9
-size 1427863863
+oid sha256:c450f836f017007a742704fc9f469acae8d94e2a6e785151016532c4b680f7ef
+size 1324906489