Upload folder using huggingface_hub

README.md

@@ -23,10 +23,10 @@ Llama-NextGen-8b is a merge of the following models using [LazyMergekit](https:/
 slices:
   - sources:
     - model: chuanli11/Llama-3.2-3B-Instruct-uncensored
-      layer_range: [8, 28]
+      layer_range: [0, 12]
   - sources:
     - model: bunnycore/Llama-3.2-3B-Mix
-      layer_range: [0, 14]
+      layer_range: [8, 28]
 merge_method: passthrough
 tokenizer_source: union
 dtype: float16

config.json

@@ -20,7 +20,7 @@
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 24,
-  "num_hidden_layers": 34,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

mergekit_config.yml

@@ -3,10 +3,10 @@
 slices:
   - sources:
     - model: chuanli11/Llama-3.2-3B-Instruct-uncensored
-      layer_range: [8, 28]
+      layer_range: [0, 12]
   - sources:
     - model: bunnycore/Llama-3.2-3B-Mix
-      layer_range: [0, 14]
+      layer_range: [8, 28]
 merge_method: passthrough
 tokenizer_source: union
 dtype: float16

model-00002-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9bc59fc44f3984524eae4d2dcf3244c5b13b22ed1a0b65067e82633725189ac
-size 989351160
+oid sha256:f0dae561cf6e239bb730cc41c6f957276b5a51aeb5a59e4784a06cf01390798d
+size 989351144

model-00003-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52f8d75f6c4f4899444dd16721f7decd9f02c4dbae69221aedc757e8320f549
-size 994110120
+oid sha256:ef380e6b512c25b257835ab0528c1fe8f59e385d3a17448ad0ada576493240ee
+size 994110136

model-00004-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60993de3bb3d1882e868185d5d6540092864f44450c99101ee7039de2ced6357
-size 994116592
+oid sha256:21c155bd06b504d378191695b43cd2096f0a01f716243bdde5fdfd72a667268f
+size 994116616

model-00005-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0916741e0e95c64c93d89c56e1c2fd98633dfd9b502eca143931e26485802dd
-size 987825016
+oid sha256:784a9a69421981638a50fb8e6625d1dd61ded5b8fb531123c716cf1817c2fa99
+size 987825040

model-00006-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdeeef8aa090d95a4f4e941b6237d192052c6a30e712be4800248ac9e5691f9e
+oid sha256:0e5f51c822c47d2a02e0553b4a7905b50f1f44ea18fb9de9e1534dd3d76f2a67
 size 950069936

model-00007-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6862c2e26e0f8679949a85052d0c9b40a21b30e5c800704fc2b3768abe8a95f
-size 956367768
+oid sha256:4c7c0c910307314c8e08b76788c9951c6ce761211abf371631c145f9414b2e71
+size 956367752

model-00008-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb089ff2a8f98d6a9d004afcd0d3eb959b3662fb94c21f66fcc6d54e8c1858a6
-size 956374024
+oid sha256:1b2ca01ec9bc4d6ccfa902d1b5c1ce715682fd82b5bac47a2792dc75617d7d2e
+size 956373984

model-00009-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d627999b98ce720f235a1ff3b249fc3c83a280ec778a1acefd3d8e76c3821a
-size 805353344
+oid sha256:2822a3b503815743516862a5b971f88e5ed96860a7a88d3f8110af8b2665b9a1
+size 402673552

model.safetensors.index.json

@@ -1 +1 @@
-{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 8421537792}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00002-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 8018860032}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00002-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}