Upload LlamaForCausalLM

config.json

@@ -1,27 +1,27 @@
 {
-  "_name_or_path": "/workspace/new/pretraining/local-models/training/2024-02-11_05-09-18",
+  "_name_or_path": "/workspace/new/pretraining/local-models/training/2024-02-11_05-17-50",
   "architectures": [
-    "RobertaForCausalLM"
+    "LlamaForCausalLM"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 50256,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0,
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 1026,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 8,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
-  "type_vocab_size": 1,
-  "use_cache": false,
-  "vocab_size": 50265
+  "use_cache": true,
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
+  "bos_token_id": 1,
   "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 sha256:5c6cf33bce3ccb7b13daa654965c384c5c9208b117325d15ba8253b7268cb71b
-size 500386812
+oid sha256:cd89560c54d5d27c64939ab79c6dade05631b25de2f61a8bcd9518c85fee4886
+size 733541408