Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sft/output/1T_FT_lr1e-5_ep5_top1_2024-03-04/checkpoint-575",
+  "_name_or_path": "./output/1431k_samsung_qa_FT_lr2e-4_ep3_top1_2024-05-01_/checkpoint-1536",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
@@ -22,7 +23,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.0.dev0",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 32001
 }

generation_config.json

@@ -1,4 +1,4 @@
 {
   "max_new_tokens": 32,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.41.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e96303cbe4faa0bf7e8a9129635538fe455c5a3c4de9014fde97a57acfa13e
-size 4400216536
+oid sha256:7668889fce16c6a0c31d7f4583cf1a9b32cabcd9485a3a3ea44c546dd433c849
+size 4400232920