Upload OPTForCausalLM

config.json

@@ -1,32 +1,31 @@
 {
-  "_name_or_path": "ccore/getcode-350m",
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "LlamaForCausalLM"
+    "OPTForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 960,
-  "initializer_range": 0.02,
-  "intermediate_size": 2560,
-  "is_llama_config": true,
-  "max_position_embeddings": 8192,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 15,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 5,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_interleaved": false,
-  "rope_scaling": null,
-  "rope_theta": 100000,
-  "tie_word_embeddings": true,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "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": "4.47.0",
   "use_cache": true,
-  "vocab_size": 49152
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab237cb7a4a12b5913039477bbfb178aac5c8809b3264af22d9311f26c092d4
-size 1447317080
+oid sha256:b4304e4463b24eaeea8ae1a18477af8a8a00c3b8d51d9688f3179f0514ef8602
+size 1324830880