Upload LlamaForCausalLM

config.json

@@ -11,7 +11,8 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -22,7 +23,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.41.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.41.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf617ab8b2d725d231a7a0dc1c1d55c53d310056b119b84de51eac9c82e542d9
+oid sha256:f2c144103072514542e327fa8080bd375cb300f2d453fba9ca3aea81d0d4cf33
 size 4976698672

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b234a42c7b589c25b9400167b36daa8e062f90b02f6e8d6fc8d83eb8a43b90
+oid sha256:5dc34e6bdf2da9e35f0d93b5c333c870f3677dc43dc3a91ea3a8ad28a1fe1acb
 size 1168138808