Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/finetuning-subnet/local-models/training/2024-01-30_21-00-30",
+  "_name_or_path": "/finetuning-subnet/local-models/training/2024-01-31_18-23-10",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": true,
-  "vocab_size": 32000
+  "use_cache": false,
+  "vocab_size": 32002
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "transformers_version": "4.36.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f5c5da7fe4ecdc897b054e08f24d17af89f947ae09fb80ff666d400bc49abb
-size 4943162336
+oid sha256:c72cd474842e226ccafc77b2e3be70e8eab48a785387ebdcd59b15a818ac6b43
+size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e843546cb73b37092944b22dd5255f70d8f6ce7309d40f1995739a42480e80c
+oid sha256:c72ba01dc739e783498877b2c694cc375f1f5597b79d2eb0e16aa54040b75bb2
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e395d0409b070060adebf33b0d70b1219f1202d36d1667b337125a78967794
-size 4540516344
+oid sha256:6d5a8fcabe3a55315f29f2846646598ca3fa15ad371aa131c029d4ce81492cf9
+size 4540532728

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 14483496960
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",