Add balanced/verbose variants: rename s30 to -balanced, restore rl100 as -verbose

.gitattributes

@@ -37,3 +37,7 @@ TwIL-8B-F16.gguf filter=lfs diff=lfs merge=lfs -text
 TwIL-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 TwIL-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 TwIL-8B-evaluation-report.pdf filter=lfs diff=lfs merge=lfs -text
+TwIL-8B-Q4_K_M-balanced.gguf filter=lfs diff=lfs merge=lfs -text
+TwIL-8B-F16-verbose.gguf filter=lfs diff=lfs merge=lfs -text
+TwIL-8B-Q8_0-verbose.gguf filter=lfs diff=lfs merge=lfs -text
+TwIL-8B-Q4_K_M-verbose.gguf filter=lfs diff=lfs merge=lfs -text

TwIL-8B-F16-verbose.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d8f7d35d82c38e845f23612513ac49333e5fa23a1788d843449124e13b64bd
+size 17587420608

TwIL-8B-Q4_K_M-balanced.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bda82d2608ca61b6aca48394f212349ef1515d0d9a2e6edee06619152faa0e
+size 5347917568

TwIL-8B-Q4_K_M-verbose.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5646abbb98f6ab81cfb9f7590aef894011ba50a259fb5d5aac8284d154e64ef0
+size 5347917248

TwIL-8B-Q8_0-verbose.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6242f84e5d9854ca54a9f39dd14dadbd9eaad5b3d2bc6195d408cae69e8f85d6
+size 9345613248

model-balanced.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fe4b7e42b45d15f43c10e1e2fa0602409bcc8cad03911aa0d8c4a0846e3532
+size 17583228544

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 17583185920
+  },
+  "weight_map": {
+    "lm_head.weight": "model-balanced.safetensors",
+    "model.embed_tokens.weight": "model-balanced.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-balanced.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-balanced.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-balanced.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-balanced.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-balanced.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-balanced.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-balanced.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-balanced.safetensors",
+    "model.norm.weight": "model-balanced.safetensors"
+  }
+}

verbose/chat_template.jinja

@@ -0,0 +1,184 @@
+{%- macro tool_to_json(tool) -%}
+    {%- set ns_tool = namespace(first=true) -%}
+    {{- '{' -}}
+    {%- for k, v in tool.items() -%}
+        {%- if k != 'defer_loading' and k != 'strict' -%}
+            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
+            {%- set ns_tool.first = false -%}
+            {{- '"' ~ k ~ '": ' ~ (v | tojson(ensure_ascii=False)) -}}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- endmacro -%}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
+{%- set low_effort = low_effort if low_effort is defined else False %}
+{%- if reasoning_effort is defined and reasoning_effort is not none %}
+    {%- set low_effort = reasoning_effort == "low" %}
+{%- endif %}
+{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
+
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- set loop_messages = messages %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{# Recompute last_user_idx relative to loop_messages after handling system #}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\n" }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- if system_message is defined and system_message | length > 0 %}
+        {{- "\n\n" }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {%- if tool.defer_loading is not defined or not tool.defer_loading %}
+            {{- '\n' ~ tool_to_json(tool) }}
+        {%- endif %}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+
+
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" %}
+        {# Add reasoning content in to content field for unified processing below. #}
+        {%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+            {%- set content = "<think>\n" ~ message.reasoning_content ~ "\n</think>\n" ~ (message.content | default('', true)) %}
+        {%- else %}
+            {%- set content = message.content | default('', true) %}
+            {%- if content is string -%}
+                {# Allow downstream logic to to take care of broken thought, only handle coherent reasoning here. #}
+                {%- if '<think>' not in content and '</think>' not in content -%}
+                    {%- set content = "<think></think>" ~ content -%}
+                {%- endif -%}
+            {%- else -%}
+                {%- set content = content -%}
+            {%- endif -%}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+            {# Assistant message has tool calls. #}
+            {{- '<|im_start|>assistant\n' }}
+                {%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {%- if content is string and content | trim | length > 0 %}
+                    {%- if include_content %}
+                        {{- (content | trim) ~ '\n' -}}
+                    {%- else %}
+                        {%- set c = (content | string) %}
+                        {%- if '</think>' in c %}
+                            {# Keep only content after the last closing think. Also generation prompt causes this. #}
+                            {%- set c = c.split('</think>')[-1] %}
+                        {%- elif '<think>' in c %}
+                            {# If <think> was opened but never closed, drop the trailing think segment #}
+                            {%- set c = c.split('<think>')[0] %}
+                        {%- endif %}
+                        {%- set c = "<think></think>" ~ c | trim %}
+                        {%- if c | length > 0 %}
+                            {{- c ~ '\n' -}}
+                        {%- endif %}
+                    {%- endif %}
+                {%- else %}
+                    {{- "<think></think>" -}}
+                {%- endif %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
+                        {%- if tool_call.arguments is defined %}
+                            {%- for args_name, args_value in tool_call.arguments|items %}
+                                {{- '<parameter=' ~ args_name ~ '>\n' -}}
+                                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                                {{- args_value ~ '\n</parameter>\n' -}}
+                            {%- endfor %}
+                        {%- endif %}
+                    {{- '</function>\n</tool_call>\n' -}}
+                {%- endfor %}
+                {{- '<|im_end|>\n' }}
+        {%- else %}
+            {# Assistant message doesn't have tool calls. #}
+            {%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
+            {%- else %}
+                {%- set c = (content | default('', true) | string) %}
+                {%- if '<think>' in c and '</think>' in c %}
+                    {%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
+                {%- endif %}
+                {%- set c = c | trim %}
+                {%- if c | length > 0 %}
+                    {{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
+                {%- else %}
+                    {{- '<|im_start|>assistant\n<|im_end|>\n' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+    {%- elif message.role == "user" or message.role == "system" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- set content = message.content | string %}
+        {%- if message.role == "user" and loop.index0 == ns.last_user_idx and low_effort %}
+            {{- content + '\n\n{reasoning effort: low}' }}
+        {%- else %}
+            {{- content }}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {%- if enable_thinking %}
+        {{- '<|im_start|>assistant\n<think>\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant\n<think></think>' }}
+    {%- endif %}
+{%- endif %}

verbose/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 100283,
+  "dtype": "bfloat16",
+  "embedding_multiplier": 1.0,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.1,
+  "intermediate_size": 12800,
+  "logits_scaling": 1.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 100257,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.3",
+  "use_cache": true,
+  "vocab_size": 100352
+}

verbose/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100283,
+  "do_sample": true,
+  "eos_token_id": 100257,
+  "pad_token_id": 100257,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.5.3"
+}

verbose/model-verbose.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f582543fcb077e8672e6c05aba680e3d90b35601390817cea1af20ff2733fbd1
+size 17583228544

verbose/model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 17583185920
+  },
+  "weight_map": {
+    "lm_head.weight": "model-verbose.safetensors",
+    "model.embed_tokens.weight": "model-verbose.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-verbose.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-verbose.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-verbose.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-verbose.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-verbose.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-verbose.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-verbose.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-verbose.safetensors",
+    "model.norm.weight": "model-verbose.safetensors"
+  }
+}

verbose/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<unk>"
+}