Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/workspace/sn6/snapshots/1c1b8027b2c5da1e7e7710f6491d5f09e8b1cb17",
+  "_name_or_path": "/workspace/finetuning-subnet/local-models/training/2024-02-03_17-00-46",
   "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:d7b00b10b104e3df1d582c7b90a8d5e361319c7e83d3ca20042d5892f3d5a94e
-size 4943162336
+oid sha256:a874ba59a6f96da9e423f044e32783104dfab2db46befccf696f88f939fd71c5
+size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e14a9a27eee0a0e2c4fb30aebee54de95f727e1bdff4e87c4438495b75e6ac6
+oid sha256:0a74ca0f31d8acb7c27848fbd94eb84e4432365d2dcc16770b9e5ff65ba7f06a
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54775f6965de7873f5caa18628daad0182a888c9a07ef5200da45d3cd282ec33
-size 4540516344
+oid sha256:e5202a12e76697363fcbf4cd5ed2db8ca6e29d435b4c32b068aa5aa56700f159
+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",