Upload FalconForCausalLM

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b-instruct",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForTokenClassification"
+  },
+  "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": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40be3a0b0b68f390b54387ec90e715bf7cbb195eaedc91748aeb68b16c90ef2c
+size 1679753728

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78ad04a1a89ccfb5ada506523797d61b5fddee6d175bee39744e14c535408b9
+size 1986965728

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0315586037fa810c121b62e3839e1bef1c791a5db9282b01fccec3752b7ad9
+size 1824072328

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5846ced3ef2854f1073e2b56becda70aa763744da6a0851733e67f9fc5121fcc
+size 1986929160

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac8a0642ba1872db92060a7a83504e5ceda5818866a42295aa252dd5141c23e
+size 1986965728

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1252a1522f3565ed19939917c12bde381868ee80651994ea68b0440ea3d131d
+size 1824072344

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d885e490b435a9f6451f990ca59300bb6e888e7ae7338bf5930cce0d04f134
+size 1986929176

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f510333f681ab60f28e4b4a84f0460fd24e961cea7ba387fe147f60e7e946e
+size 1986965744

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb705d981c7ab31bf6c87256b58bac860537b25ed4a6c82388f3cb73fc843c1
+size 1824072344

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20496ffc91e818c2a14549cc51542c96c32be97605e035e9316915bd5c8cbf3
+size 1986929176

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f92fcb51800244f3fc46b11c366c34037f3fc510ad17d235d8fccb4f057a83
+size 1986965744

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf5707edd5e4924367faccc56bc0e6052de314d06f6c520d7e775958a17d88a
+size 1824072344

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dab5313cf073eb72cc1b8308c5a3d28f5c08448f154ea181d1d90713d4945b7
+size 1986929176

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e38f20537aeaf35f4ef9a4cbf37da446417697e580a4938b3a28f9323083374
+size 1986965744

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd53008d78a64898d2809e82f97ad4d2f016d0a8be5956d135fbb9b5eda9b5c
+size 828317584

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 27686882816
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00002-of-00015.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00002-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-00006-of-00015.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00006-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-00007-of-00015.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00007-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-00008-of-00015.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00008-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-00009-of-00015.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00009-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-00010-of-00015.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00010-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-00011-of-00015.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00011-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-00012-of-00015.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00012-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-00013-of-00015.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00013-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-00014-of-00015.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00014-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-00003-of-00015.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00003-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-00015-of-00015.safetensors",
+    "transformer.h.31.input_layernorm.weight": "model-00015-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-00004-of-00015.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00004-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-00005-of-00015.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00005-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"
+  }
+}