Adding `safetensors` variant of this model

model.safetensors.index.json

@@ -0,0 +1,309 @@
+{
+    "metadata": {
+        "total_size": 14400036864
+    },
+    "weight_map": {
+        "h.0.input_layernorm.weight": "model_00002-of-00032.safetensors",
+        "h.0.mlp.down_proj.bias": "model_00002-of-00032.safetensors",
+        "h.0.mlp.down_proj.weight": "model_00002-of-00032.safetensors",
+        "h.0.mlp.gate_proj.weight": "model_00002-of-00032.safetensors",
+        "h.0.mlp.up_proj.weight": "model_00002-of-00032.safetensors",
+        "h.0.post_attention_layernorm.weight": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.dense.bias": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.dense.weight": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.key_value.weight": "model_00002-of-00032.safetensors",
+        "h.0.self_attention.query.weight": "model_00002-of-00032.safetensors",
+        "h.1.input_layernorm.weight": "model_00003-of-00032.safetensors",
+        "h.1.mlp.down_proj.bias": "model_00003-of-00032.safetensors",
+        "h.1.mlp.down_proj.weight": "model_00003-of-00032.safetensors",
+        "h.1.mlp.gate_proj.weight": "model_00003-of-00032.safetensors",
+        "h.1.mlp.up_proj.weight": "model_00003-of-00032.safetensors",
+        "h.1.post_attention_layernorm.weight": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.dense.bias": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.dense.weight": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.key_value.weight": "model_00003-of-00032.safetensors",
+        "h.1.self_attention.query.weight": "model_00003-of-00032.safetensors",
+        "h.10.input_layernorm.weight": "model_00012-of-00032.safetensors",
+        "h.10.mlp.down_proj.bias": "model_00012-of-00032.safetensors",
+        "h.10.mlp.down_proj.weight": "model_00012-of-00032.safetensors",
+        "h.10.mlp.gate_proj.weight": "model_00012-of-00032.safetensors",
+        "h.10.mlp.up_proj.weight": "model_00012-of-00032.safetensors",
+        "h.10.post_attention_layernorm.weight": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.dense.bias": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.dense.weight": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.key_value.weight": "model_00012-of-00032.safetensors",
+        "h.10.self_attention.query.weight": "model_00012-of-00032.safetensors",
+        "h.11.input_layernorm.weight": "model_00013-of-00032.safetensors",
+        "h.11.mlp.down_proj.bias": "model_00013-of-00032.safetensors",
+        "h.11.mlp.down_proj.weight": "model_00013-of-00032.safetensors",
+        "h.11.mlp.gate_proj.weight": "model_00013-of-00032.safetensors",
+        "h.11.mlp.up_proj.weight": "model_00013-of-00032.safetensors",
+        "h.11.post_attention_layernorm.weight": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.dense.bias": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.dense.weight": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.key_value.weight": "model_00013-of-00032.safetensors",
+        "h.11.self_attention.query.weight": "model_00013-of-00032.safetensors",
+        "h.12.input_layernorm.weight": "model_00014-of-00032.safetensors",
+        "h.12.mlp.down_proj.bias": "model_00014-of-00032.safetensors",
+        "h.12.mlp.down_proj.weight": "model_00014-of-00032.safetensors",
+        "h.12.mlp.gate_proj.weight": "model_00014-of-00032.safetensors",
+        "h.12.mlp.up_proj.weight": "model_00014-of-00032.safetensors",
+        "h.12.post_attention_layernorm.weight": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.dense.bias": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.dense.weight": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.key_value.weight": "model_00014-of-00032.safetensors",
+        "h.12.self_attention.query.weight": "model_00014-of-00032.safetensors",
+        "h.13.input_layernorm.weight": "model_00015-of-00032.safetensors",
+        "h.13.mlp.down_proj.bias": "model_00015-of-00032.safetensors",
+        "h.13.mlp.down_proj.weight": "model_00015-of-00032.safetensors",
+        "h.13.mlp.gate_proj.weight": "model_00015-of-00032.safetensors",
+        "h.13.mlp.up_proj.weight": "model_00015-of-00032.safetensors",
+        "h.13.post_attention_layernorm.weight": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.dense.bias": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.dense.weight": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.key_value.weight": "model_00015-of-00032.safetensors",
+        "h.13.self_attention.query.weight": "model_00015-of-00032.safetensors",
+        "h.14.input_layernorm.weight": "model_00016-of-00032.safetensors",
+        "h.14.mlp.down_proj.bias": "model_00016-of-00032.safetensors",
+        "h.14.mlp.down_proj.weight": "model_00016-of-00032.safetensors",
+        "h.14.mlp.gate_proj.weight": "model_00016-of-00032.safetensors",
+        "h.14.mlp.up_proj.weight": "model_00016-of-00032.safetensors",
+        "h.14.post_attention_layernorm.weight": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.dense.bias": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.dense.weight": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.key_value.weight": "model_00016-of-00032.safetensors",
+        "h.14.self_attention.query.weight": "model_00016-of-00032.safetensors",
+        "h.15.input_layernorm.weight": "model_00017-of-00032.safetensors",
+        "h.15.mlp.down_proj.bias": "model_00017-of-00032.safetensors",
+        "h.15.mlp.down_proj.weight": "model_00017-of-00032.safetensors",
+        "h.15.mlp.gate_proj.weight": "model_00017-of-00032.safetensors",
+        "h.15.mlp.up_proj.weight": "model_00017-of-00032.safetensors",
+        "h.15.post_attention_layernorm.weight": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.dense.bias": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.dense.weight": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.key_value.weight": "model_00017-of-00032.safetensors",
+        "h.15.self_attention.query.weight": "model_00017-of-00032.safetensors",
+        "h.16.input_layernorm.weight": "model_00018-of-00032.safetensors",
+        "h.16.mlp.down_proj.bias": "model_00018-of-00032.safetensors",
+        "h.16.mlp.down_proj.weight": "model_00018-of-00032.safetensors",
+        "h.16.mlp.gate_proj.weight": "model_00018-of-00032.safetensors",
+        "h.16.mlp.up_proj.weight": "model_00018-of-00032.safetensors",
+        "h.16.post_attention_layernorm.weight": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.dense.bias": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.dense.weight": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.key_value.weight": "model_00018-of-00032.safetensors",
+        "h.16.self_attention.query.weight": "model_00018-of-00032.safetensors",
+        "h.17.input_layernorm.weight": "model_00019-of-00032.safetensors",
+        "h.17.mlp.down_proj.bias": "model_00019-of-00032.safetensors",
+        "h.17.mlp.down_proj.weight": "model_00019-of-00032.safetensors",
+        "h.17.mlp.gate_proj.weight": "model_00019-of-00032.safetensors",
+        "h.17.mlp.up_proj.weight": "model_00019-of-00032.safetensors",
+        "h.17.post_attention_layernorm.weight": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.dense.bias": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.dense.weight": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.key_value.weight": "model_00019-of-00032.safetensors",
+        "h.17.self_attention.query.weight": "model_00019-of-00032.safetensors",
+        "h.18.input_layernorm.weight": "model_00020-of-00032.safetensors",
+        "h.18.mlp.down_proj.bias": "model_00020-of-00032.safetensors",
+        "h.18.mlp.down_proj.weight": "model_00020-of-00032.safetensors",
+        "h.18.mlp.gate_proj.weight": "model_00020-of-00032.safetensors",
+        "h.18.mlp.up_proj.weight": "model_00020-of-00032.safetensors",
+        "h.18.post_attention_layernorm.weight": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.dense.bias": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.dense.weight": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.key_value.weight": "model_00020-of-00032.safetensors",
+        "h.18.self_attention.query.weight": "model_00020-of-00032.safetensors",
+        "h.19.input_layernorm.weight": "model_00021-of-00032.safetensors",
+        "h.19.mlp.down_proj.bias": "model_00021-of-00032.safetensors",
+        "h.19.mlp.down_proj.weight": "model_00021-of-00032.safetensors",
+        "h.19.mlp.gate_proj.weight": "model_00021-of-00032.safetensors",
+        "h.19.mlp.up_proj.weight": "model_00021-of-00032.safetensors",
+        "h.19.post_attention_layernorm.weight": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.dense.bias": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.dense.weight": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.key_value.weight": "model_00021-of-00032.safetensors",
+        "h.19.self_attention.query.weight": "model_00021-of-00032.safetensors",
+        "h.2.input_layernorm.weight": "model_00004-of-00032.safetensors",
+        "h.2.mlp.down_proj.bias": "model_00004-of-00032.safetensors",
+        "h.2.mlp.down_proj.weight": "model_00004-of-00032.safetensors",
+        "h.2.mlp.gate_proj.weight": "model_00004-of-00032.safetensors",
+        "h.2.mlp.up_proj.weight": "model_00004-of-00032.safetensors",
+        "h.2.post_attention_layernorm.weight": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.dense.bias": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.dense.weight": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.key_value.weight": "model_00004-of-00032.safetensors",
+        "h.2.self_attention.query.weight": "model_00004-of-00032.safetensors",
+        "h.20.input_layernorm.weight": "model_00022-of-00032.safetensors",
+        "h.20.mlp.down_proj.bias": "model_00022-of-00032.safetensors",
+        "h.20.mlp.down_proj.weight": "model_00022-of-00032.safetensors",
+        "h.20.mlp.gate_proj.weight": "model_00022-of-00032.safetensors",
+        "h.20.mlp.up_proj.weight": "model_00022-of-00032.safetensors",
+        "h.20.post_attention_layernorm.weight": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.dense.bias": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.dense.weight": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.key_value.weight": "model_00022-of-00032.safetensors",
+        "h.20.self_attention.query.weight": "model_00022-of-00032.safetensors",
+        "h.21.input_layernorm.weight": "model_00023-of-00032.safetensors",
+        "h.21.mlp.down_proj.bias": "model_00023-of-00032.safetensors",
+        "h.21.mlp.down_proj.weight": "model_00023-of-00032.safetensors",
+        "h.21.mlp.gate_proj.weight": "model_00023-of-00032.safetensors",
+        "h.21.mlp.up_proj.weight": "model_00023-of-00032.safetensors",
+        "h.21.post_attention_layernorm.weight": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.dense.bias": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.dense.weight": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.key_value.weight": "model_00023-of-00032.safetensors",
+        "h.21.self_attention.query.weight": "model_00023-of-00032.safetensors",
+        "h.22.input_layernorm.weight": "model_00024-of-00032.safetensors",
+        "h.22.mlp.down_proj.bias": "model_00024-of-00032.safetensors",
+        "h.22.mlp.down_proj.weight": "model_00024-of-00032.safetensors",
+        "h.22.mlp.gate_proj.weight": "model_00024-of-00032.safetensors",
+        "h.22.mlp.up_proj.weight": "model_00024-of-00032.safetensors",
+        "h.22.post_attention_layernorm.weight": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.dense.bias": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.dense.weight": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.key_value.weight": "model_00024-of-00032.safetensors",
+        "h.22.self_attention.query.weight": "model_00024-of-00032.safetensors",
+        "h.23.input_layernorm.weight": "model_00025-of-00032.safetensors",
+        "h.23.mlp.down_proj.bias": "model_00025-of-00032.safetensors",
+        "h.23.mlp.down_proj.weight": "model_00025-of-00032.safetensors",
+        "h.23.mlp.gate_proj.weight": "model_00025-of-00032.safetensors",
+        "h.23.mlp.up_proj.weight": "model_00025-of-00032.safetensors",
+        "h.23.post_attention_layernorm.weight": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.dense.bias": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.dense.weight": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.key_value.weight": "model_00025-of-00032.safetensors",
+        "h.23.self_attention.query.weight": "model_00025-of-00032.safetensors",
+        "h.24.input_layernorm.weight": "model_00026-of-00032.safetensors",
+        "h.24.mlp.down_proj.bias": "model_00026-of-00032.safetensors",
+        "h.24.mlp.down_proj.weight": "model_00026-of-00032.safetensors",
+        "h.24.mlp.gate_proj.weight": "model_00026-of-00032.safetensors",
+        "h.24.mlp.up_proj.weight": "model_00026-of-00032.safetensors",
+        "h.24.post_attention_layernorm.weight": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.dense.bias": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.dense.weight": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.key_value.weight": "model_00026-of-00032.safetensors",
+        "h.24.self_attention.query.weight": "model_00026-of-00032.safetensors",
+        "h.25.input_layernorm.weight": "model_00027-of-00032.safetensors",
+        "h.25.mlp.down_proj.bias": "model_00027-of-00032.safetensors",
+        "h.25.mlp.down_proj.weight": "model_00027-of-00032.safetensors",
+        "h.25.mlp.gate_proj.weight": "model_00027-of-00032.safetensors",
+        "h.25.mlp.up_proj.weight": "model_00027-of-00032.safetensors",
+        "h.25.post_attention_layernorm.weight": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.dense.bias": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.dense.weight": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.key_value.weight": "model_00027-of-00032.safetensors",
+        "h.25.self_attention.query.weight": "model_00027-of-00032.safetensors",
+        "h.26.input_layernorm.weight": "model_00028-of-00032.safetensors",
+        "h.26.mlp.down_proj.bias": "model_00028-of-00032.safetensors",
+        "h.26.mlp.down_proj.weight": "model_00028-of-00032.safetensors",
+        "h.26.mlp.gate_proj.weight": "model_00028-of-00032.safetensors",
+        "h.26.mlp.up_proj.weight": "model_00028-of-00032.safetensors",
+        "h.26.post_attention_layernorm.weight": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.dense.bias": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.dense.weight": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.key_value.weight": "model_00028-of-00032.safetensors",
+        "h.26.self_attention.query.weight": "model_00028-of-00032.safetensors",
+        "h.27.input_layernorm.weight": "model_00029-of-00032.safetensors",
+        "h.27.mlp.down_proj.bias": "model_00029-of-00032.safetensors",
+        "h.27.mlp.down_proj.weight": "model_00029-of-00032.safetensors",
+        "h.27.mlp.gate_proj.weight": "model_00029-of-00032.safetensors",
+        "h.27.mlp.up_proj.weight": "model_00029-of-00032.safetensors",
+        "h.27.post_attention_layernorm.weight": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.dense.bias": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.dense.weight": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.key_value.weight": "model_00029-of-00032.safetensors",
+        "h.27.self_attention.query.weight": "model_00029-of-00032.safetensors",
+        "h.28.input_layernorm.weight": "model_00030-of-00032.safetensors",
+        "h.28.mlp.down_proj.bias": "model_00030-of-00032.safetensors",
+        "h.28.mlp.down_proj.weight": "model_00030-of-00032.safetensors",
+        "h.28.mlp.gate_proj.weight": "model_00030-of-00032.safetensors",
+        "h.28.mlp.up_proj.weight": "model_00030-of-00032.safetensors",
+        "h.28.post_attention_layernorm.weight": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.dense.bias": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.dense.weight": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.key_value.weight": "model_00030-of-00032.safetensors",
+        "h.28.self_attention.query.weight": "model_00030-of-00032.safetensors",
+        "h.29.input_layernorm.weight": "model_00031-of-00032.safetensors",
+        "h.29.mlp.down_proj.bias": "model_00031-of-00032.safetensors",
+        "h.29.mlp.down_proj.weight": "model_00031-of-00032.safetensors",
+        "h.29.mlp.gate_proj.weight": "model_00031-of-00032.safetensors",
+        "h.29.mlp.up_proj.weight": "model_00031-of-00032.safetensors",
+        "h.29.post_attention_layernorm.weight": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.dense.bias": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.dense.weight": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.key_value.weight": "model_00031-of-00032.safetensors",
+        "h.29.self_attention.query.weight": "model_00031-of-00032.safetensors",
+        "h.3.input_layernorm.weight": "model_00005-of-00032.safetensors",
+        "h.3.mlp.down_proj.bias": "model_00005-of-00032.safetensors",
+        "h.3.mlp.down_proj.weight": "model_00005-of-00032.safetensors",
+        "h.3.mlp.gate_proj.weight": "model_00005-of-00032.safetensors",
+        "h.3.mlp.up_proj.weight": "model_00005-of-00032.safetensors",
+        "h.3.post_attention_layernorm.weight": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.dense.bias": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.dense.weight": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.key_value.weight": "model_00005-of-00032.safetensors",
+        "h.3.self_attention.query.weight": "model_00005-of-00032.safetensors",
+        "h.4.input_layernorm.weight": "model_00006-of-00032.safetensors",
+        "h.4.mlp.down_proj.bias": "model_00006-of-00032.safetensors",
+        "h.4.mlp.down_proj.weight": "model_00006-of-00032.safetensors",
+        "h.4.mlp.gate_proj.weight": "model_00006-of-00032.safetensors",
+        "h.4.mlp.up_proj.weight": "model_00006-of-00032.safetensors",
+        "h.4.post_attention_layernorm.weight": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.dense.bias": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.dense.weight": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.key_value.weight": "model_00006-of-00032.safetensors",
+        "h.4.self_attention.query.weight": "model_00006-of-00032.safetensors",
+        "h.5.input_layernorm.weight": "model_00007-of-00032.safetensors",
+        "h.5.mlp.down_proj.bias": "model_00007-of-00032.safetensors",
+        "h.5.mlp.down_proj.weight": "model_00007-of-00032.safetensors",
+        "h.5.mlp.gate_proj.weight": "model_00007-of-00032.safetensors",
+        "h.5.mlp.up_proj.weight": "model_00007-of-00032.safetensors",
+        "h.5.post_attention_layernorm.weight": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.dense.bias": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.dense.weight": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.key_value.weight": "model_00007-of-00032.safetensors",
+        "h.5.self_attention.query.weight": "model_00007-of-00032.safetensors",
+        "h.6.input_layernorm.weight": "model_00008-of-00032.safetensors",
+        "h.6.mlp.down_proj.bias": "model_00008-of-00032.safetensors",
+        "h.6.mlp.down_proj.weight": "model_00008-of-00032.safetensors",
+        "h.6.mlp.gate_proj.weight": "model_00008-of-00032.safetensors",
+        "h.6.mlp.up_proj.weight": "model_00008-of-00032.safetensors",
+        "h.6.post_attention_layernorm.weight": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.dense.bias": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.dense.weight": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.key_value.weight": "model_00008-of-00032.safetensors",
+        "h.6.self_attention.query.weight": "model_00008-of-00032.safetensors",
+        "h.7.input_layernorm.weight": "model_00009-of-00032.safetensors",
+        "h.7.mlp.down_proj.bias": "model_00009-of-00032.safetensors",
+        "h.7.mlp.down_proj.weight": "model_00009-of-00032.safetensors",
+        "h.7.mlp.gate_proj.weight": "model_00009-of-00032.safetensors",
+        "h.7.mlp.up_proj.weight": "model_00009-of-00032.safetensors",
+        "h.7.post_attention_layernorm.weight": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.dense.bias": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.dense.weight": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.key_value.weight": "model_00009-of-00032.safetensors",
+        "h.7.self_attention.query.weight": "model_00009-of-00032.safetensors",
+        "h.8.input_layernorm.weight": "model_00010-of-00032.safetensors",
+        "h.8.mlp.down_proj.bias": "model_00010-of-00032.safetensors",
+        "h.8.mlp.down_proj.weight": "model_00010-of-00032.safetensors",
+        "h.8.mlp.gate_proj.weight": "model_00010-of-00032.safetensors",
+        "h.8.mlp.up_proj.weight": "model_00010-of-00032.safetensors",
+        "h.8.post_attention_layernorm.weight": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.dense.bias": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.dense.weight": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.key_value.weight": "model_00010-of-00032.safetensors",
+        "h.8.self_attention.query.weight": "model_00010-of-00032.safetensors",
+        "h.9.input_layernorm.weight": "model_00011-of-00032.safetensors",
+        "h.9.mlp.down_proj.bias": "model_00011-of-00032.safetensors",
+        "h.9.mlp.down_proj.weight": "model_00011-of-00032.safetensors",
+        "h.9.mlp.gate_proj.weight": "model_00011-of-00032.safetensors",
+        "h.9.mlp.up_proj.weight": "model_00011-of-00032.safetensors",
+        "h.9.post_attention_layernorm.weight": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.dense.bias": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.dense.weight": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.key_value.weight": "model_00011-of-00032.safetensors",
+        "h.9.self_attention.query.weight": "model_00011-of-00032.safetensors",
+        "ln_f.weight": "model_00032-of-00032.safetensors",
+        "word_embeddings.weight": "model_00001-of-00032.safetensors"
+    }
+}

model_00001-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556b983983462cf0ced16ff9b10adc81f753ef96b998e417cdbc0b0eaf7c0adf
+size 1312817288

model_00002-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d07841a04997ef05cf31c99c3569808388b83ab4af50f58b58d950e26d5fe2a
+size 436241424

model_00003-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0038354562dd55c122b08284138267b72f4545c48564223e38e081a3eb3a6f
+size 436241424

model_00004-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe807fc83148692b2ec70e918664c02d22ea6f89b365dde16329dc7999beb887
+size 436241424

model_00005-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41b236a81d35c2aef4f36428bb930cb23985d2ca972e6669aadc994a50dac58
+size 436241424

model_00006-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a6d02efa14f3803c99ff8431e32db10a324259c813c7bb359c7b4d5cd41a97f
+size 436241424

model_00007-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36606ee9f6741f01bc33f5afe7bea73584ff420606ff4b40933bd9f112f3da6f
+size 436241424

model_00008-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc5d37ea020e0ad99589a9d51b35b35ea0fe76ad1a634a36980debcb4d16400
+size 436241424

model_00009-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b756a9f2b0e7a28e16702179e5433813b4bcb48a7ca5f2bd5772a1d85dd34321
+size 436241424

model_00010-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ed0c1042f3062985a5bf6bfb99c51fe4ff276afec16fd7e848621798920da7
+size 436241424

model_00011-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655e1bbf708b67c33e250ef6671575654d60691271d7c6d54d88981c4da89bd7
+size 436241424

model_00012-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ba8f41864ffff13df9dba654006dd61bae37a1b2c14fc4296e9a544b06c7ae
+size 436241432

model_00013-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7724008a24175457d81bdd9277db6994eb68592e4feadae779fd8cbfa69bdbd8
+size 436241432

model_00014-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47410f36efe7c42d1c0e91afcf1f3aaecccabdf5ace91b32f2a13a7b71b9f111
+size 436241432

model_00015-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32913deea454acbb070637aed2100e3bff2113acffd53eaf3f7f58862586a1df
+size 436241432

model_00016-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13141a727092e5e33a125be5fb46b0ba0a336ab7061dbb378ed5683e82b3546
+size 436241432

model_00017-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d82c20329c3043f9dda91862c741a1169d48e729d6eddfac414506f4e235d9
+size 436241432

model_00018-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5ab7bc4ba0d031db392687e0a69e18a19d93e85245cd09ee24d4d6688a8b59
+size 436241432

model_00019-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614365ced74c8e8fc627336a3c88ddfd4f0a1e4de3d4bdec1ea2028c9f4cdda7
+size 436241432

model_00020-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183a12959f09bbf775c1dc0b8dd8b73d06540e5c3f33af424adaa00867273a71
+size 436241432

model_00021-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65883d7503c3c25f8a42efba949a87c26120e80232228f96971511a77bed7ac6
+size 436241432

model_00022-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f31513119aed1bd6164e65f23279dc054bb31a9e934aab0792d54ef24786dc
+size 436241432

model_00023-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d15bb43c898d8a1826ac55bb51660b2ec219953f399d01fb75fd2867e9ef261
+size 436241432

model_00024-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae95648ac37ae15198e9c938b090085c4b555fbd8d6dbcb24fa2fa380047e153
+size 436241432

model_00025-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6b4590d594fc3fe5be2c8a791d4153eaadb635009617e46deb8249305d2220
+size 436241432

model_00026-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e6ac79bf617752319e67f22384f717c85d88a480f45aee81cb487ac95e387d
+size 436241432

model_00027-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a89bbd6758d20d76da31ccdc55afd007b377316c38e4070972a64e8b39c713
+size 436241432

model_00028-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee5676f9aba0f1ab94511df1b1e0872843f9fd91a9126cf49d7e6d3895ecd47
+size 436241432

model_00029-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315d3c41be7a8c5a2d3efd8b7af044d03c3fade6ceb24f986ed5bd2d96c2b824
+size 436241432

model_00030-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fafc37807f22d35cf9e8e0949daa4b98fca7dd3fc022ba5af6527aa97decf3f
+size 436241432

model_00031-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e296f5c162857c10d763a1a81ed998c4a743c5c079fbe924b115bfc27fcd3c10
+size 436241432

model_00032-of-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd05006bfcdb8199627fe470dedb7cb94705f1cf2f9ffd6d45048e5b5508186
+size 8304