Upload GemmaForCausalLM

README.md

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/gemma-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",
+  "hidden_activation": null,
+  "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_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "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": "4.40.1"
+}

model-00001-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd94bdaab8cda14f29b2a9933115ccad1105864f6f1a1167c061b8a2592a450
+size 1572864144

model-00002-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d39301fd602fe336e8ce3cf6ef0fa8c5bc1f806a9f072a51c511d7ee1528ac
+size 956315336

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fed97166f55b4b04292ef4d03879fdf151848ce3523bf8b79ae219bf217fe01
+size 956327848

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d678d542a452107e3b052bc8d5750eb4739b65209cd4b8955b5a76e7f097bc
+size 956327848

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858556b16400a09a9697a6ea4ef55db257e246740932f96b2d5132deed3f3582
+size 855651576

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46720d7bc40a42b83c02d11f0157a155adbcae966c9c1c5e01eef68e529cc816
+size 956327848

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98abe8ccde54a92d789aaefdb802fd59dca429909dfd1e2802e8ca6f978d964d
+size 956327856

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750bc2647300aa85724b2a7631eff9d3a93eb281322c93dde412d2064ac904d8
+size 855651592

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310c1599550b0c936ad312f4e6228e9520cd0a58bc1079acec2b4ac4d2256234
+size 956327864

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6309ab4176ab01031e4482684e1dec357129502d522fb5bb77b29795ad01ebbe
+size 956327864

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a305aab77bf682339b266f607d5a5c4ff7f438038d4d5f4aefdc6b65cbc7f1
+size 855651592

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1591af3256ae521a00073e2b20311dd032649f6437983569daee12648efaa6
+size 956327864

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf3c04d5413db25ec3855d874f328a052ec2ce274c3cbb5ce5a5eeac94fb747
+size 956327864

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d7ea879fa9dce11c0979705944627f857fbcdeb04e04a2c6960d1acc8216af
+size 855651592

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3801692cde743db4537aebdea6947b2654bfa09987a1888d5bb458c580d3637
+size 956327864

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6808d2cf6de03309960a2a0b24c46876f4b8c6afbd4e8dc45dcf5c2bb9e34ff8
+size 956327864

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a21ddfb64886277931c413e5bec04f17f224585cdaaf692771d631bf63ca30
+size 855651592

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd85d09ba5878c2c70c6b93044b6fc9adea069dd02492bb534e19736afc5619
+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"
+  }
+}