Upload folder using huggingface_hub (#2)

- 50730b4190088945a6da9fd5035c7eaec609a30be6068c13779dbacd5eb6e1a2 (b96a20a7f15d12b9ca9c770da805544feb6a553a)
- c3bfb91dc78621aa6f5aa630042e6dc8745e61bf5e973093a8ae32c747a0b1c2 (6d694c8ba0a236dad9f3ec7c27e4fa8c08463652)
- 00cec71e51b9014539bf09b3991c3739fd170dd5ac93d7b66a05762043fa53ed (61d1ed0ac517e90dcf5461e19dedff56bf847ffa)

config.json

@@ -1,5 +1,5 @@
 {
-    "_name_or_path": "/covalent/.cache/models/tmpl0dooqs33mbjpzya",
+    "_name_or_path": "/covalent/.cache/models/tmped9bmhvsju5cwczt",
     "architectures": [
         "LlamaForCausalLM"
     ],
@@ -20,7 +20,7 @@
     "mlp_bias": false,
     "model_type": "llama",
     "num_attention_heads": 32,
-    "num_hidden_layers": 31,
+    "num_hidden_layers": 32,
     "num_key_value_heads": 8,
     "pad_token_id": 128004,
     "pretraining_tp": 1,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605d9d315c745da44dc1978e6d93752af07b15696be5077a1f37ce6b6064aaaf
+oid sha256:1809ed2a03ad626cf842a3b23ebb12bcd961d046584b96a1866022d2f63e3a42
 size 4996772687

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce79c2c29a31b7831d945d6f77eb3fe78081982bb43996f6f511b168d70bd71
-size 3871719490
+oid sha256:516fb1124ecede3b7fa433594df126871f13fe25d5ed69cf94830f9adaac99b4
+size 4090014257

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8868413657
+    "total_size": 9086705888
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -580,6 +580,29 @@
     "model.layers.30.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.weight_format": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_format": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",

smash_config.json

@@ -28,7 +28,7 @@
     "quant_llm-int8_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/covalent/.cache/models/tmpl0dooqs3",
+    "cache_dir": "/covalent/.cache/models/tmped9bmhvs",
     "task": "",
     "save_load_fn": "bitsandbytes",
     "save_load_fn_args": {}