Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/finetuning-subnet/local-models/training/2024-01-30_18-01-35",
+  "_name_or_path": "/finetuning-subnet/local-models/training/3HrIntervalSaved",
   "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 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.36.2"
+  "eos_token_id": 32000,
+  "transformers_version": "4.36.2",
+  "use_cache": false
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd620dfdeea3bf73e6366b939c9cbe3d56207284258bef1b61c68555859294c
-size 4943162336
+oid sha256:0568faf693a8d8256e7de885f1b6e2d00d5d450dbaebee705de883fb7a60ddce
+size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c7d9a23dde3ca0262eac1ff1f6eba4e8d527f29b8a4658a697d899eeabb8cf
+oid sha256:cfb20fd1895ebed978cf29ec634603a9853eeb594d4c7876b81a3446bb392410
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2ebc657be92b1d312fb460d0d401c1214325d9bca84546487ad418f13ca7b9d
-size 4540516344
+oid sha256:780b7794e8480b64499f86e70ddce2552bd9e558b8a9272577676fd0d0567c08
+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",