Upload Olmo1124ForCausalLM

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13b6d269fd625d100841189b7f484998cbc7b0fb0db86918de3421ace09ec663
-size 4949546136
+oid sha256:cd3044e11b7a772f513b4f7b95a50252738c8d61030dcb212dfb8b82fb92c1a2
+size 4949546184

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae93f29c9a1a4a7e83b6d3187d4f81a49f84f4046d3c0db32873ad7b86ed1314
-size 4991622744
+oid sha256:46ff6494a75b1933e5c653875e56d06ee724856973a9308164d2671fe55baa2b
+size 4991622816

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848a9b542af31616be04bede890951feb295d7afec60e94d65ec43ee645e2976
-size 4924546824
+oid sha256:eb459f4a7d5a8989e55b528ee6d424156822b9b150df60b5faea0f53f4013df2
+size 4924546896

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c26770bb047719f07f3a6c9e373260c9580adeec592affe1b396cd3ab0c92e2
-size 4857404856
+oid sha256:972f150775e39ac52954db51fd559af3e397df847d8ab2ad9be2a079a8ccc8e4
+size 4857404928

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df8bd3dc6188f65eefec90dd3c3a49f63732d32406e57439b81ec964ee963e9
-size 4857404856
+oid sha256:fc3f00bb6c5f820381516cc4e51ca68fd11d5e6c34bed666b0edf2e507ff5184
+size 4857404928

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4288952b99a6a105507a839a600bd35332dbc526301ec86ca805253288311f70
-size 4613984752
+oid sha256:c69fb469d2d3cef04e6ef794f2ff69be35a2702a52740fa1bcb2b91744a4f867
+size 4613984792

model.safetensors.index.json

@@ -5,352 +5,352 @@
   "weight_map": {
     "lm_head.weight": "model-00006-of-00006.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",