model-attribution-challenge
/

opt-350m

Text Generation Transformers PyTorch TensorFlow JAX English opt text-generation-inference

Model card Files Files and versions Community

ArthurZ HF staff commited on May 17, 2022

Commit

31d113e

•

1 Parent(s): 414672d

add model

Files changed (2) hide show

config.json +5 -5
flax_model.msgpack +3 -0

config.json CHANGED Viewed

@@ -2,15 +2,15 @@
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
-    "OPTForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "hidden_size": 1024,
   "do_layer_norm_before": false,
   "dropout": 0.1,
   "eos_token_id": 2,
   "ffn_dim": 4096,
   "init_std": 0.02,
   "layerdrop": 0.0,
   "max_position_embeddings": 2048,
@@ -18,10 +18,10 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "torch_dtype": "float16",
-  "transformers_version": "4.19.0.dev0",
   "use_cache": true,
   "vocab_size": 50272,
-  "word_embed_proj_dim": 512,
-  "prefix": "</s>"
 }

   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
+    "OPTModel"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "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,
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
   "pad_token_id": 1,
+  "prefix": "</s>",
   "torch_dtype": "float16",
+  "transformers_version": "4.20.0.dev0",
   "use_cache": true,
   "vocab_size": 50272,
+  "word_embed_proj_dim": 512
 }

flax_model.msgpack ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e70fc2225b84a806461f18321e9fc0761f1cb649801abe42a5e894b0e11ad891
+size 662406360