Upload RWForCausalLM

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b-instruct",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_RW.RWConfig",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modelling_RW.RWForCausalLM"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.31.0.dev0"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22b2c7425abdcbf2d50986e209ac2f8b73afcbcd0e555a9299bf6e52ebe566a
+size 1679790280

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd862f6b8aeeff3735ea53b01c26e305053edee6dc2df16bf857c5da2d53fbc9
+size 1986965752

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23536f2859f4bee312ff856b40ce6d9a209eee231fa3bf4667a2e7deb72d77b1
+size 1824072352

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cafba110ff037d261ba5f25976c210cb42877049834afd4ba1b64f111919af7
+size 1986929176

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5338841ea89a57f1ab3492acb04f6a590e602398cb5cb857551945b0b8a4533c
+size 1986965736

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fd9e1c3db0a402798983e5faca15f3396de00c33226aeb82cd7f1bbd07536b
+size 1824072368

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b1bb55ce01a5a4f6f5a6d6656ee0798e94b0ddc6f52218a09e7d6614a162e6
+size 1986929192

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede083616580619f8e37b6ebd3756c701930a3fc4a9df59bcf3c79b07c4e1bf4
+size 1986965768

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087911a79378d63e6ac4a199d13aeac8947d00020a870e710db9d1a8ea4bdebf
+size 1824072368

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebda63ca06ccf6b9e3809dc69632a242124e44cb9e07a8d3b3356dd4dcd4840d
+size 1986929192

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fb1dbfc84b48ec1e628f856cb3f30531bd80600470f0f55a47cb10f1aaa7ba
+size 1986965768

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fc371f7c0100dc1d6fda58dff9bb7d41ad65062efda4f8ace211f3b4f59c80
+size 1824072368

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873d3635e8060d94e85d449b494c4c6644c10de758e928891f349f5da348b7ed
+size 1986929192

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8c1dac7869ec25c370c13ef8b81fe8168b7f8614e1452d6eb37d65d3ec20d8
+size 1986965768

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8020319f796ff381158c3c293271cf30f8c70bf2af68ca88750feb8778c01d52
+size 828281024

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 27686882816
+  },
+  "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-00002-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-00002-of-00015.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00002-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-00002-of-00015.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00002-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-00006-of-00015.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00006-of-00015.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00006-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-00007-of-00015.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00007-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-00007-of-00015.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00007-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-00008-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-00008-of-00015.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00008-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-00008-of-00015.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00008-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-00009-of-00015.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00009-of-00015.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00009-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-00010-of-00015.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00010-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-00010-of-00015.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00010-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-00011-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-00011-of-00015.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00011-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-00011-of-00015.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00011-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-00012-of-00015.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00012-of-00015.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00012-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-00013-of-00015.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00013-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-00013-of-00015.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00013-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-00014-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-00014-of-00015.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00014-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-00014-of-00015.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00014-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-00003-of-00015.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00003-of-00015.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00003-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-00015-of-00015.safetensors",
+    "transformer.h.31.self_attention.dense.weight": "model-00015-of-00015.safetensors",
+    "transformer.h.31.self_attention.query_key_value.weight": "model-00015-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-00004-of-00015.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00004-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-00004-of-00015.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00004-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-00005-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-00005-of-00015.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00005-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-00005-of-00015.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00005-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"
+  }
+}