add model

README.md

@@ -0,0 +1,47 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: opt-125m
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# opt-125m
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: None
+- training_precision: float32
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.20.0.dev0
+- TensorFlow 2.9.1
+- Datasets 2.2.2
+- Tokenizers 0.12.1

config.json

@@ -1,11 +1,12 @@
 {
+  "_name_or_path": "facebook/opt-125m",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
-    "OPTForCausalLM"
+    "OPTModel"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
+  "bos_token_id": 2,
   "do_layer_norm_before": true,
   "dropout": 0.1,
   "eos_token_id": 2,
@@ -19,7 +20,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "prefix": "</s>",
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.20.0.dev0",
   "use_cache": true,
   "vocab_size": 50272,

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbcad992d2c5b0a967d1178bf88f3a3273136f84cdcce59f5fa2b0a1215bad0
+size 501162056