Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/workspace/finetuning-subnet/local-models/training/2024-02-01_21-42-37",
+  "_name_or_path": "/workspace/sn6/snapshots/1c1b8027b2c5da1e7e7710f6491d5f09e8b1cb17",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "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": false,
-  "vocab_size": 32002
+  "use_cache": true,
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "transformers_version": "4.36.2",
-  "use_cache": false
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283393d140c771edcfa2c12f3651ae71d38badcc10c077a26cf4fed70aa85428
-size 4943178720
+oid sha256:d7b00b10b104e3df1d582c7b90a8d5e361319c7e83d3ca20042d5892f3d5a94e
+size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de3d297584327cf975fc87e18631a51c262f604beddef48b85cc4ddad92234e
+oid sha256:6e14a9a27eee0a0e2c4fb30aebee54de95f727e1bdff4e87c4438495b75e6ac6
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397fa3d73bcdf84742a6035dbc9f41b85cc27d7e2c1a69c494f4a3c6f99104b6
-size 4540532728
+oid sha256:54775f6965de7873f5caa18628daad0182a888c9a07ef5200da45d3cd282ec33
+size 4540516344

model.safetensors.index.json

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