Upload GemmaForCausalLM

README.md

@@ -8,10 +8,10 @@ tags:
 - lora
 - generated_from_trainer
 base_model: google/gemma-7b-it
+pipeline_tag: text-generation
 model-index:
 - name: train_2024-05-01-08-42-24
   results: []
-pipeline_tag: text-generation
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

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 sha256:45f53b550712b8f727670ece0b12b019f22ccfa22e482e47822b9cccbde8aad5
+size 956315336

model-00003-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd0b0bf8b6630606517bda05aca6de5424885e565543775443b4d674a6a34cb
+size 956327848

model-00004-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a46476dc4a0f1a98b6f40df1f63e164fddf2f81964ab9a2c102298703941ac
+size 956327848

model-00005-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e602c7709971d119a1d0db20de227b00ceef0a5bd3e41c9aca552a957bb8855c
+size 855651576

model-00006-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5d14a86d968b93c72b9c81eda2db75009a4518d4705b543258dba388e17a2e
+size 956327848

model-00007-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4d84ee25047c8108b609ee2a8826cec59fc8f8a515dfed19a19befa3c60573
+size 956327856

model-00008-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc58027b8ac9fa42be32a0fb471a843cca0089f888f9937608386137a048b462
+size 855651592

model-00009-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1533dd207bdf14d63b3b466a956fa25abea73b1d5687dcc52e2cb3542fae88a0
+size 956327864

model-00010-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31596ced25dd5afd93bf93ea2297b77bbd4069d3b1e041c1f5713f462d71ed7
+size 956327864

model-00011-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1147bf983bf31c32d1b8bf68fc718756120c1d3ea79ceaa95b22595d6e2356
+size 855651592

model-00012-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813ffccf9f788dc9e4b0a47686ee2ac708c3324dc450a0325f2349e2bc90c3ae
+size 956327864

model-00013-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c490f00d531f268fceaafdc1376b428cc235e3d5254b9b26d9963340430eeffc
+size 956327864

model-00014-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c147bc9642d523bea6595ee4b8fad82878666e77ea708eca81728a132477cb0c
+size 855651592

model-00015-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5faddf02ce1f08f2c00bcc32182630f7871164a072139ad713e9086b31679b0b
+size 956327864

model-00016-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf7d0893c449eaa3d860a0773e8061fd9da5669841491a05957aecd2d54eb79
+size 956327864

model-00017-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754e564150e79f69d483ace1c537c8701a3d8b12bd13d02700785e3acfea5d62
+size 855651592

model-00018-of-00018.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6f3c97768cb65ca63bf768deed140a9cab4c6326b84be3163c36c8189b308f
+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"
+  }
+}