Upload LlamaForCausalLM

config.json

@@ -1,46 +1,27 @@
 {
-  "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-05_15-45-02",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
+  "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-06_15-49-30",
   "architectures": [
-    "BartForCausalLM"
+    "LlamaForCausalLM"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 15,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 15,
+  "attention_bias": false,
+  "bos_token_id": 1,
   "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
-  "is_decoder": true,
-  "is_encoder_decoder": false,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "num_hidden_layers": 15,
-  "pad_token_id": 1,
-  "scale_embedding": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "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",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,9 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
+  "bos_token_id": 1,
   "eos_token_id": 2,
-  "forced_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:cb18b56acef83df3ee3316edcba6b91295355cfcccc9c412e51e702c9cffbe96
-size 724724784
+oid sha256:30ef164aa20550b26a8c4aa7d4984e24f7828371c37f564d0d4d214e78ed41f9
+size 733541408