removed pickles and split into smaller shards the safetensors

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": ".",
+  "_name_or_path": "/gpfs/projects/bsc88/tools/aguila-7b",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
@@ -21,15 +21,15 @@
   "hidden_size": 4544,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
   "model_type": "RefinedWebModel",
   "multi_query": true,
   "n_head": 71,
   "n_layer": 32,
   "pad_token_id": 50256,
   "parallel_attn": true,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.30.2",
   "use_cache": true,
-  "max_position_embeddings": 2048,
   "vocab_size": 50257
-}
+}

model-00001-of-00002.safetensors → model-00001-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ee43ebc4b14760c2a94baa24213f0f37f2a5e9b07a6e6488f4376265830d7b
-size 9981994344
+oid sha256:c1e5b97f5ac8b84a16da79b0cd4d2ac660424f4a3f655dbb0cbbdb7784743ef7
+size 1909299216

model-00002-of-00002.safetensors → model-00002-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e85ec13d59bfc6c6f84bc0e7419ad03776a119d739dbe4f006c2dd87bbc71c
-size 3727267912
+oid sha256:13700ed44b712d0f762b1719a6ee2cfc8d2659c800abdf30e247f573d6ed210f
+size 1986929176

pytorch_model-00001-of-00002.bin → model-00003-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71df7f76b33ae5afd2d6185422944e5063cd69d065cb73421ffdaae1bca4ef9e
-size 9982026522
+oid sha256:6b84ab4f3c73bacb562641c4fe426f757fb51615efd14ca1ca3663071dc8008e
+size 1986965752

pytorch_model-00002-of-00002.bin → model-00004-of-00015.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ad1f3e7abd726291a34fb5e8d80c3e5c2025bc3f137bbd6fa8a9cb081057eb
-size 3727279707
+oid sha256:ec939c0bca9ed24a14b89afb4bfc6d4e23f0ce232197d84a17f13ed3d5aba0f8
+size 1824072352

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c46816a9da3f260fd7d64708fc87502c4449a0429f27b6dfee3aecebe469ba
+size 1986929168

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4042f69ea71c4985063e70872fa99173cf4ec006d7c9a15fc6a8b8cc712a0c2a
+size 1986965768

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931719bbe3d98645fc70c8e22df68636cc2f504a14dd41354e544ce346bf36ac
+size 1824072368

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1d16c2321080d8f71e6396a1a1d6adf8b5866629d2a5cb7f12fec73958ebe9
+size 1986929192

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a760dcf799420983a7db9ebf49bb9c6bc004042d6a51cfdfd07c68abec0c6740
+size 1986965768

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e4da7be6ebf8c20057d8364c261126efeeceb56b2d190be3ccbf6f82b8f085
+size 1824072368

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590115bd785f5862835fbe023cb98ebc05d4c4f9310bc301a577283e0fb880b8
+size 1986929192

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8957a361fa3558b14bfadb08e6e1c6611b2a8c70de914af861672fd614ae72bc
+size 1986965768

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c7954b3c32e36900223d0725f7ec5e31951dc553aa7740dd8791a2c31cd584
+size 1824072368

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10dd2988a936abd107ee5c317e38ffa6f446acd781325440d890a0a28fb159a6
+size 1986929192

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93796669d72c8c5a962b346eaf158454f52531b7b7231683020f73760fb7d6a5
+size 330403664

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 27418477824
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00015.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00015.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00005-of-00015.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00006-of-00015.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00006-of-00015.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00006-of-00015.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00007-of-00015.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00007-of-00015.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00008-of-00015.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00008-of-00015.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00009-of-00015.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00009-of-00015.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00002-of-00015.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00009-of-00015.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00010-of-00015.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00010-of-00015.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00011-of-00015.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00011-of-00015.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00012-of-00015.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00012-of-00015.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00012-of-00015.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00013-of-00015.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00013-of-00015.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00002-of-00015.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
+    "transformer.h.30.input_layernorm.bias": "model-00014-of-00015.safetensors",
+    "transformer.h.30.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.self_attention.dense.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.30.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.31.input_layernorm.bias": "model-00014-of-00015.safetensors",
+    "transformer.h.31.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00015-of-00015.safetensors",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.31.self_attention.dense.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.31.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00003-of-00015.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00003-of-00015.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00003-of-00015.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00004-of-00015.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00004-of-00015.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00005-of-00015.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00005-of-00015.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
+    "transformer.ln_f.bias": "model-00015-of-00015.safetensors",
+    "transformer.ln_f.weight": "model-00015-of-00015.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00015.safetensors"
+  }
+}