1fde032c6306fe8d91a4d15e035a1d22ec52cdb9848bf56d4cb431325f47c0e9

config.json

@@ -1,5 +1,5 @@
 {
-    "_name_or_path": "/covalent/.cache/models/tmpluu9d7tw2yfe3gap",
+    "_name_or_path": "/covalent/.cache/models/tmp57bf60qtms7lqfzq",
     "architectures": [
         "KPhi3ForCausalLM"
     ],
@@ -25,7 +25,7 @@
     "num_hidden_layers": 4,
     "num_key_value_heads": 20,
     "original_max_position_embeddings": 4096,
-    "pad_token_id": 0,
+    "pad_token_id": 32000,
     "quantization_config": {
         "_load_in_4bit": false,
         "_load_in_8bit": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0110234d8d49d564914daa53228c675cc0e0fa665aacd5a3ea87e82528c504df
+oid sha256:77208107c40186ffe47a1d95c6195cd33ea97995a7e3af9c0e2d54db0670bd5e
 size 201550688

smash_config.json

@@ -28,7 +28,7 @@
     "quant_llm-int8_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/covalent/.cache/models/tmpluu9d7tw",
+    "cache_dir": "/covalent/.cache/models/tmp57bf60qt",
     "task": "",
     "save_load_fn": "bitsandbytes",
     "save_load_fn_args": {}