Upload OPTForCausalLM

config.json

@@ -1,27 +1,31 @@
 {
-  "_name_or_path": "/pretraining/local-models/training/2024-01-17_19-57-00",
+  "_name_or_path": "TrainingModel/",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "LlamaForCausalLM"
+    "OPTForCausalLM"
   ],
-  "attention_bias": false,
-  "bos_token_id": 1,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
   "eos_token_id": 2,
-  "hidden_act": "silu",
+  "ffn_dim": 3072,
   "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 2000,
-  "max_position_embeddings": 1024,
-  "model_type": "llama",
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "num_key_value_heads": 12,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": true,
+  "pad_token_id": 1,
+  "prefix": "</s>",
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
+  "bos_token_id": 2,
   "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.34.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c0ff732ccf459e55426f850b69e40d194b1ec0e9e13a05ab75afd981077dba
-size 488908744
+oid sha256:b3a67b42504e0c101c739fe6ef0d57eb3a9ed90267e41aba8019149a472ceae1
+size 500979600