Update correct weights

config.json

@@ -1,6 +1,7 @@
 {
+  "_name_or_path": "sealion7b-wemotion-3epochs",
   "architectures": [
-    "MptForCausalLM"
+    "MPTForCausalLM"
   ],
   "attn_config": {
     "alibi": false,

generation_config.json

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.31.0",
   "use_cache": false
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2165acb84a98566535e8b0af027f89d271119f95470500240c2a84be5f67274b
-size 9882121688
+oid sha256:0267ffaca9f01613b72a781237eb07beac06eff25781f5f4474ce37460414590
+size 9901337456

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e6fded9a278fb9d6c0abad75ee6ec685dc74502d0c3a1de1b11813ebf6c4e5
-size 5100487208
+oid sha256:fa2fcacc86c33ed1951f64b6a024c81b58d74d3b315483502290151f3e871e91
+size 5102024512

model.safetensors.index.json

@@ -1,201 +1,523 @@
 {
   "metadata": {
-    "total_size": 14982586368
+    "total_size": 15003303936
   },
   "weight_map": {
+    "transformer.blocks.0.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.0.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.0.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.0.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.0.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.0.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.0.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.1.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.1.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.1.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.1.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.1.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.1.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.10.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.10.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.10.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.10.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.10.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.10.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.11.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.11.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.11.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.11.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.11.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.11.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.12.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.12.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.12.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.12.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.12.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.12.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.13.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.13.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.13.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.13.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.13.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.13.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.14.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.14.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.14.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.14.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.14.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.14.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.15.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.15.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.15.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.15.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.15.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.15.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.16.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.16.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.16.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.16.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.16.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.16.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.17.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.17.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.17.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.17.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.17.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.17.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.18.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.18.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.18.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.18.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.18.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.18.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.18.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.19.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.19.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.19.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.19.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.19.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.19.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.19.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.19.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.19.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.2.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.2.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.2.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.2.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.2.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.2.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.20.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.20.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.20.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.20.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.20.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.20.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.20.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.20.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.21.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.21.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.21.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.21.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.21.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.21.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.22.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.22.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.22.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.22.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.22.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.22.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.23.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.23.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.23.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.23.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.23.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.23.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.23.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.24.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.24.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.24.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.24.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.24.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.24.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.24.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.25.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.25.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.25.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.25.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.25.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.25.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.25.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.26.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.26.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.26.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.26.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.26.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.26.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.26.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.27.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.27.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.27.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.27.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.27.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.27.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.27.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.28.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.28.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.28.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.28.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.28.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.28.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.28.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.29.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.29.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.29.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.29.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.29.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.29.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.29.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.3.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.3.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.3.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.3.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.3.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.3.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.3.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.30.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.30.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.30.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.30.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.30.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.30.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.30.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.30.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.attn.Wqkv.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.31.attn.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.attn.k_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.attn.k_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.31.attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.attn.q_ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.attn.q_ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.ffn.down_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.31.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.ffn.up_proj.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.31.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.norm_1.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.31.norm_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.31.norm_2.bias": "model-00002-of-00002.safetensors",
     "transformer.blocks.31.norm_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.blocks.4.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.4.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.4.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.4.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.4.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.4.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.4.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.5.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.5.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.5.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.5.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.5.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.5.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.6.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.6.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.6.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.6.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.6.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.6.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.7.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.7.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.7.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.7.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.7.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.7.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.8.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.8.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.8.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.8.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.8.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.8.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.attn.Wqkv.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.9.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.attn.k_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.attn.k_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.attn.q_ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.attn.q_ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.ffn.down_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.9.ffn.down_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.ffn.up_proj.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.9.ffn.up_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.norm_1.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.9.norm_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.blocks.9.norm_2.bias": "model-00001-of-00002.safetensors",
     "transformer.blocks.9.norm_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.norm_f.bias": "model-00002-of-00002.safetensors",
     "transformer.norm_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
     "transformer.wte.weight": "model-00001-of-00002.safetensors"
   }
 }