Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/finetuning-subnet/local-models/training/3HrIntervalSaved",
+  "_name_or_path": "/finetuning-subnet/local-models/training/2024-02-01_19-22-01",
   "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 sha256:4670a7dd3e117f5f70fd252fae56f62f13cb6feb4c97517a3594546cc52daa79
-size 4943162336
+oid sha256:224eb4f897ec2f07651a7146f8866acf4eec9b358a15e460d43e3e081f3280d1
+size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d526dddb937ca109106ae7bb69db0f1e20a00ba3e8527469a8b10b7b29f6dc
+oid sha256:13401545fc4fe1cf120d1ffa549f19cdc597b7e78c5c3b87d5cffa87b6b73b3b
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5aacb79efc03f6583639add1d8715098eb898cc42040bac48fd1c0da5a4c37
-size 4540516344
+oid sha256:c3fd73596a9905f1c3746f385682e6dfa85dd92360b15d88a1717a8e929c1e60
+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",