Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/usr/local/lib/python3.9/dist-packages/local-models/training/2024-02-15_06-42-29",
+  "_name_or_path": "/usr/local/lib/python3.9/dist-packages/local-models/training/2024-02-15_13-13-31",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
+  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.36.2",
-  "use_cache": false
+  "transformers_version": "4.36.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455986609aab159a4d3bc6604e3e7eec1f7e543850420594aafc7296ba71e643
+oid sha256:5bd9635d75a7f42cf20b6d1d0fc42ef65a182fb25f3aa64118196dea40d3d275
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb24ede8349f9cb7f13c0e645c1f81bf93f2223214dff2de44f7eec9de941610
+oid sha256:e0f71049dd018f0b1a2e2b3e15081db49501a39cb3401ea78d3382c102772292
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09021d3227f44658ab13770adb5ca887390b7fa6544236fbdad3cdfc486b020
+oid sha256:e4c3c5ec244ac0d689c888b8ea7d520b0e33cfc53fe6132d0918a1fc6e932d3f
 size 4540516344