Upload LlamaForCausalLM

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "llm-jp/llm-jp-3-13b-instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,15 +8,15 @@
   "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 5120,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 13824,
+  "intermediate_size": 11008,
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -39,7 +38,7 @@
   "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.52.3",
   "use_cache": false,
   "vocab_size": 99584
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.49.0"
+  "transformers_version": "4.52.3"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010f8ccaeb5b0e2845444e1c482212c0afa06ce4c7c9bd197b1e3fbab8c05936
+size 4997074831

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d0bda78d5861bf62be09d39680cc1536a06e81f8e500042083b50a71209e6d
+size 1557806297