Upload GemmaForCausalLM

README.md

@@ -3,6 +3,7 @@ license: apache-2.0
 library_name: adapter-transformers
 tags:
 - medical
+- llama-factory
 ---
 # Model Card for Model ID
 

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-1.1-7b-it",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602d61323989ba73dd85ad6698bcc1d512d15ab431fa878ca190d6870caa17f2
+size 1572864144

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb653c43fe247a60a5068f253af89f4e8e8ceb835e654aef7cdea6853f453f09
+size 956315336

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f679feba81be554356a9cbb0b7d6f9d867fdac978d21d9bf0021f9af50fca041
+size 956327848

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55134146c2637ff027510e8edd3a78afef09879580b4a7f778e48d738b4909c8
+size 956327848

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47ce7e4192b064d1474ea1ac5da9bac28e91d223dc7d4780ad3f7d1b89bf779
+size 855651576

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e60839f20a68b9047501c3292530d55d876555bfa167d6d24ec720f00f88386d
+size 956327848

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7150daddf20475ee7ed44221720011746a92f7f778e4d2f5159025e9509fbce5
+size 956327856

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4750d71d0c6ea33d6805e19e12006b729c1bd083a245e12dbafeaddd1f7bbe3
+size 855651592

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56f09f6d4bf8cc60dfbb12d407e47b6b4fa166435f9441b1221d72d03d63b36
+size 956327864

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fcd02e9f3245dd0c975dcc084b7195af040538e1c11b754df12ee6c6e56829
+size 956327864

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19eaf0aec56ce9eb9624ea9a97e33eb5ff6e8d65878f2e219fea07c7fd91c3a5
+size 855651592

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d767c46cc4181d04f7da59a09d7445e15df141bffa09fce887b1ec177c5629
+size 956327864

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5657857a0aaaba07ccd475ea52664abaa45cf107853712b932dc2fa2198cbcb
+size 956327864

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e2e3c6f1bbd13c15c1334a58e4f47d1160abacc0dd6a9438a8dd571df2687e
+size 855651592

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f7ba8c5cd24a50396fa7b21622ba474008cb241a3da0cd3228baeda36e2f0d
+size 956327864

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab0b2fe968285035e3339c0678b8b5cecc6ab56a15e9f41986bf32431856576
+size 956327864

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a7560a359c6a399fd894527c84fcfb3bcfda4000e8f4acb097a832dbd9e013
+size 855651592

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7655fe1cdbbc3df7e407cfc9fc4ce84585103032c55b825d7b38908d0bc1683a
+size 704675280

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00018.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
+    "model.norm.weight": "model-00018-of-00018.safetensors"
+  }
+}