Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

hf_quant_config.json

@@ -12,394 +12,473 @@
             "model.layers.0.self_attn.indexer*",
             "model.layers.0.self_attn.kv_a_proj_with_mqa",
             "model.layers.0.self_attn.kv_b_proj",
+            "model.layers.0.self_attn.o_proj",
             "model.layers.0.self_attn.q_a_proj",
             "model.layers.0.self_attn.q_b_proj",
             "model.layers.1.self_attn.indexer*",
             "model.layers.1.self_attn.kv_a_proj_with_mqa",
             "model.layers.1.self_attn.kv_b_proj",
+            "model.layers.1.self_attn.o_proj",
             "model.layers.1.self_attn.q_a_proj",
             "model.layers.1.self_attn.q_b_proj",
             "model.layers.10.self_attn.indexer*",
             "model.layers.10.self_attn.kv_a_proj_with_mqa",
             "model.layers.10.self_attn.kv_b_proj",
+            "model.layers.10.self_attn.o_proj",
             "model.layers.10.self_attn.q_a_proj",
             "model.layers.10.self_attn.q_b_proj",
             "model.layers.11.self_attn.indexer*",
             "model.layers.11.self_attn.kv_a_proj_with_mqa",
             "model.layers.11.self_attn.kv_b_proj",
+            "model.layers.11.self_attn.o_proj",
             "model.layers.11.self_attn.q_a_proj",
             "model.layers.11.self_attn.q_b_proj",
             "model.layers.12.self_attn.indexer*",
             "model.layers.12.self_attn.kv_a_proj_with_mqa",
             "model.layers.12.self_attn.kv_b_proj",
+            "model.layers.12.self_attn.o_proj",
             "model.layers.12.self_attn.q_a_proj",
             "model.layers.12.self_attn.q_b_proj",
             "model.layers.13.self_attn.indexer*",
             "model.layers.13.self_attn.kv_a_proj_with_mqa",
             "model.layers.13.self_attn.kv_b_proj",
+            "model.layers.13.self_attn.o_proj",
             "model.layers.13.self_attn.q_a_proj",
             "model.layers.13.self_attn.q_b_proj",
             "model.layers.14.self_attn.indexer*",
             "model.layers.14.self_attn.kv_a_proj_with_mqa",
             "model.layers.14.self_attn.kv_b_proj",
+            "model.layers.14.self_attn.o_proj",
             "model.layers.14.self_attn.q_a_proj",
             "model.layers.14.self_attn.q_b_proj",
             "model.layers.15.self_attn.indexer*",
             "model.layers.15.self_attn.kv_a_proj_with_mqa",
             "model.layers.15.self_attn.kv_b_proj",
+            "model.layers.15.self_attn.o_proj",
             "model.layers.15.self_attn.q_a_proj",
             "model.layers.15.self_attn.q_b_proj",
             "model.layers.16.self_attn.indexer*",
             "model.layers.16.self_attn.kv_a_proj_with_mqa",
             "model.layers.16.self_attn.kv_b_proj",
+            "model.layers.16.self_attn.o_proj",
             "model.layers.16.self_attn.q_a_proj",
             "model.layers.16.self_attn.q_b_proj",
             "model.layers.17.self_attn.indexer*",
             "model.layers.17.self_attn.kv_a_proj_with_mqa",
             "model.layers.17.self_attn.kv_b_proj",
+            "model.layers.17.self_attn.o_proj",
             "model.layers.17.self_attn.q_a_proj",
             "model.layers.17.self_attn.q_b_proj",
             "model.layers.18.self_attn.indexer*",
             "model.layers.18.self_attn.kv_a_proj_with_mqa",
             "model.layers.18.self_attn.kv_b_proj",
+            "model.layers.18.self_attn.o_proj",
             "model.layers.18.self_attn.q_a_proj",
             "model.layers.18.self_attn.q_b_proj",
             "model.layers.19.self_attn.indexer*",
             "model.layers.19.self_attn.kv_a_proj_with_mqa",
             "model.layers.19.self_attn.kv_b_proj",
+            "model.layers.19.self_attn.o_proj",
             "model.layers.19.self_attn.q_a_proj",
             "model.layers.19.self_attn.q_b_proj",
             "model.layers.2.self_attn.indexer*",
             "model.layers.2.self_attn.kv_a_proj_with_mqa",
             "model.layers.2.self_attn.kv_b_proj",
+            "model.layers.2.self_attn.o_proj",
             "model.layers.2.self_attn.q_a_proj",
             "model.layers.2.self_attn.q_b_proj",
             "model.layers.20.self_attn.indexer*",
             "model.layers.20.self_attn.kv_a_proj_with_mqa",
             "model.layers.20.self_attn.kv_b_proj",
+            "model.layers.20.self_attn.o_proj",
             "model.layers.20.self_attn.q_a_proj",
             "model.layers.20.self_attn.q_b_proj",
             "model.layers.21.self_attn.indexer*",
             "model.layers.21.self_attn.kv_a_proj_with_mqa",
             "model.layers.21.self_attn.kv_b_proj",
+            "model.layers.21.self_attn.o_proj",
             "model.layers.21.self_attn.q_a_proj",
             "model.layers.21.self_attn.q_b_proj",
             "model.layers.22.self_attn.indexer*",
             "model.layers.22.self_attn.kv_a_proj_with_mqa",
             "model.layers.22.self_attn.kv_b_proj",
+            "model.layers.22.self_attn.o_proj",
             "model.layers.22.self_attn.q_a_proj",
             "model.layers.22.self_attn.q_b_proj",
             "model.layers.23.self_attn.indexer*",
             "model.layers.23.self_attn.kv_a_proj_with_mqa",
             "model.layers.23.self_attn.kv_b_proj",
+            "model.layers.23.self_attn.o_proj",
             "model.layers.23.self_attn.q_a_proj",
             "model.layers.23.self_attn.q_b_proj",
             "model.layers.24.self_attn.indexer*",
             "model.layers.24.self_attn.kv_a_proj_with_mqa",
             "model.layers.24.self_attn.kv_b_proj",
+            "model.layers.24.self_attn.o_proj",
             "model.layers.24.self_attn.q_a_proj",
             "model.layers.24.self_attn.q_b_proj",
             "model.layers.25.self_attn.indexer*",
             "model.layers.25.self_attn.kv_a_proj_with_mqa",
             "model.layers.25.self_attn.kv_b_proj",
+            "model.layers.25.self_attn.o_proj",
             "model.layers.25.self_attn.q_a_proj",
             "model.layers.25.self_attn.q_b_proj",
             "model.layers.26.self_attn.indexer*",
             "model.layers.26.self_attn.kv_a_proj_with_mqa",
             "model.layers.26.self_attn.kv_b_proj",
+            "model.layers.26.self_attn.o_proj",
             "model.layers.26.self_attn.q_a_proj",
             "model.layers.26.self_attn.q_b_proj",
             "model.layers.27.self_attn.indexer*",
             "model.layers.27.self_attn.kv_a_proj_with_mqa",
             "model.layers.27.self_attn.kv_b_proj",
+            "model.layers.27.self_attn.o_proj",
             "model.layers.27.self_attn.q_a_proj",
             "model.layers.27.self_attn.q_b_proj",
             "model.layers.28.self_attn.indexer*",
             "model.layers.28.self_attn.kv_a_proj_with_mqa",
             "model.layers.28.self_attn.kv_b_proj",
+            "model.layers.28.self_attn.o_proj",
             "model.layers.28.self_attn.q_a_proj",
             "model.layers.28.self_attn.q_b_proj",
             "model.layers.29.self_attn.indexer*",
             "model.layers.29.self_attn.kv_a_proj_with_mqa",
             "model.layers.29.self_attn.kv_b_proj",
+            "model.layers.29.self_attn.o_proj",
             "model.layers.29.self_attn.q_a_proj",
             "model.layers.29.self_attn.q_b_proj",
             "model.layers.3.self_attn.indexer*",
             "model.layers.3.self_attn.kv_a_proj_with_mqa",
             "model.layers.3.self_attn.kv_b_proj",
+            "model.layers.3.self_attn.o_proj",
             "model.layers.3.self_attn.q_a_proj",
             "model.layers.3.self_attn.q_b_proj",
             "model.layers.30.self_attn.indexer*",
             "model.layers.30.self_attn.kv_a_proj_with_mqa",
             "model.layers.30.self_attn.kv_b_proj",
+            "model.layers.30.self_attn.o_proj",
             "model.layers.30.self_attn.q_a_proj",
             "model.layers.30.self_attn.q_b_proj",
             "model.layers.31.self_attn.indexer*",
             "model.layers.31.self_attn.kv_a_proj_with_mqa",
             "model.layers.31.self_attn.kv_b_proj",
+            "model.layers.31.self_attn.o_proj",
             "model.layers.31.self_attn.q_a_proj",
             "model.layers.31.self_attn.q_b_proj",
             "model.layers.32.self_attn.indexer*",
             "model.layers.32.self_attn.kv_a_proj_with_mqa",
             "model.layers.32.self_attn.kv_b_proj",
+            "model.layers.32.self_attn.o_proj",
             "model.layers.32.self_attn.q_a_proj",
             "model.layers.32.self_attn.q_b_proj",
             "model.layers.33.self_attn.indexer*",
             "model.layers.33.self_attn.kv_a_proj_with_mqa",
             "model.layers.33.self_attn.kv_b_proj",
+            "model.layers.33.self_attn.o_proj",
             "model.layers.33.self_attn.q_a_proj",
             "model.layers.33.self_attn.q_b_proj",
             "model.layers.34.self_attn.indexer*",
             "model.layers.34.self_attn.kv_a_proj_with_mqa",
             "model.layers.34.self_attn.kv_b_proj",
+            "model.layers.34.self_attn.o_proj",
             "model.layers.34.self_attn.q_a_proj",
             "model.layers.34.self_attn.q_b_proj",
             "model.layers.35.self_attn.indexer*",
             "model.layers.35.self_attn.kv_a_proj_with_mqa",
             "model.layers.35.self_attn.kv_b_proj",
+            "model.layers.35.self_attn.o_proj",
             "model.layers.35.self_attn.q_a_proj",
             "model.layers.35.self_attn.q_b_proj",
             "model.layers.36.self_attn.indexer*",
             "model.layers.36.self_attn.kv_a_proj_with_mqa",
             "model.layers.36.self_attn.kv_b_proj",
+            "model.layers.36.self_attn.o_proj",
             "model.layers.36.self_attn.q_a_proj",
             "model.layers.36.self_attn.q_b_proj",
             "model.layers.37.self_attn.indexer*",
             "model.layers.37.self_attn.kv_a_proj_with_mqa",
             "model.layers.37.self_attn.kv_b_proj",
+            "model.layers.37.self_attn.o_proj",
             "model.layers.37.self_attn.q_a_proj",
             "model.layers.37.self_attn.q_b_proj",
             "model.layers.38.self_attn.indexer*",
             "model.layers.38.self_attn.kv_a_proj_with_mqa",
             "model.layers.38.self_attn.kv_b_proj",
+            "model.layers.38.self_attn.o_proj",
             "model.layers.38.self_attn.q_a_proj",
             "model.layers.38.self_attn.q_b_proj",
             "model.layers.39.self_attn.indexer*",
             "model.layers.39.self_attn.kv_a_proj_with_mqa",
             "model.layers.39.self_attn.kv_b_proj",
+            "model.layers.39.self_attn.o_proj",
             "model.layers.39.self_attn.q_a_proj",
             "model.layers.39.self_attn.q_b_proj",
             "model.layers.4.self_attn.indexer*",
             "model.layers.4.self_attn.kv_a_proj_with_mqa",
             "model.layers.4.self_attn.kv_b_proj",
+            "model.layers.4.self_attn.o_proj",
             "model.layers.4.self_attn.q_a_proj",
             "model.layers.4.self_attn.q_b_proj",
             "model.layers.40.self_attn.indexer*",
             "model.layers.40.self_attn.kv_a_proj_with_mqa",
             "model.layers.40.self_attn.kv_b_proj",
+            "model.layers.40.self_attn.o_proj",
             "model.layers.40.self_attn.q_a_proj",
             "model.layers.40.self_attn.q_b_proj",
             "model.layers.41.self_attn.indexer*",
             "model.layers.41.self_attn.kv_a_proj_with_mqa",
             "model.layers.41.self_attn.kv_b_proj",
+            "model.layers.41.self_attn.o_proj",
             "model.layers.41.self_attn.q_a_proj",
             "model.layers.41.self_attn.q_b_proj",
             "model.layers.42.self_attn.indexer*",
             "model.layers.42.self_attn.kv_a_proj_with_mqa",
             "model.layers.42.self_attn.kv_b_proj",
+            "model.layers.42.self_attn.o_proj",
             "model.layers.42.self_attn.q_a_proj",
             "model.layers.42.self_attn.q_b_proj",
             "model.layers.43.self_attn.indexer*",
             "model.layers.43.self_attn.kv_a_proj_with_mqa",
             "model.layers.43.self_attn.kv_b_proj",
+            "model.layers.43.self_attn.o_proj",
             "model.layers.43.self_attn.q_a_proj",
             "model.layers.43.self_attn.q_b_proj",
             "model.layers.44.self_attn.indexer*",
             "model.layers.44.self_attn.kv_a_proj_with_mqa",
             "model.layers.44.self_attn.kv_b_proj",
+            "model.layers.44.self_attn.o_proj",
             "model.layers.44.self_attn.q_a_proj",
             "model.layers.44.self_attn.q_b_proj",
             "model.layers.45.self_attn.indexer*",
             "model.layers.45.self_attn.kv_a_proj_with_mqa",
             "model.layers.45.self_attn.kv_b_proj",
+            "model.layers.45.self_attn.o_proj",
             "model.layers.45.self_attn.q_a_proj",
             "model.layers.45.self_attn.q_b_proj",
             "model.layers.46.self_attn.indexer*",
             "model.layers.46.self_attn.kv_a_proj_with_mqa",
             "model.layers.46.self_attn.kv_b_proj",
+            "model.layers.46.self_attn.o_proj",
             "model.layers.46.self_attn.q_a_proj",
             "model.layers.46.self_attn.q_b_proj",
             "model.layers.47.self_attn.indexer*",
             "model.layers.47.self_attn.kv_a_proj_with_mqa",
             "model.layers.47.self_attn.kv_b_proj",
+            "model.layers.47.self_attn.o_proj",
             "model.layers.47.self_attn.q_a_proj",
             "model.layers.47.self_attn.q_b_proj",
             "model.layers.48.self_attn.indexer*",
             "model.layers.48.self_attn.kv_a_proj_with_mqa",
             "model.layers.48.self_attn.kv_b_proj",
+            "model.layers.48.self_attn.o_proj",
             "model.layers.48.self_attn.q_a_proj",
             "model.layers.48.self_attn.q_b_proj",
             "model.layers.49.self_attn.indexer*",
             "model.layers.49.self_attn.kv_a_proj_with_mqa",
             "model.layers.49.self_attn.kv_b_proj",
+            "model.layers.49.self_attn.o_proj",
             "model.layers.49.self_attn.q_a_proj",
             "model.layers.49.self_attn.q_b_proj",
             "model.layers.5.self_attn.indexer*",
             "model.layers.5.self_attn.kv_a_proj_with_mqa",
             "model.layers.5.self_attn.kv_b_proj",
+            "model.layers.5.self_attn.o_proj",
             "model.layers.5.self_attn.q_a_proj",
             "model.layers.5.self_attn.q_b_proj",
             "model.layers.50.self_attn.indexer*",
             "model.layers.50.self_attn.kv_a_proj_with_mqa",
             "model.layers.50.self_attn.kv_b_proj",
+            "model.layers.50.self_attn.o_proj",
             "model.layers.50.self_attn.q_a_proj",
             "model.layers.50.self_attn.q_b_proj",
             "model.layers.51.self_attn.indexer*",
             "model.layers.51.self_attn.kv_a_proj_with_mqa",
             "model.layers.51.self_attn.kv_b_proj",
+            "model.layers.51.self_attn.o_proj",
             "model.layers.51.self_attn.q_a_proj",
             "model.layers.51.self_attn.q_b_proj",
             "model.layers.52.self_attn.indexer*",
             "model.layers.52.self_attn.kv_a_proj_with_mqa",
             "model.layers.52.self_attn.kv_b_proj",
+            "model.layers.52.self_attn.o_proj",
             "model.layers.52.self_attn.q_a_proj",
             "model.layers.52.self_attn.q_b_proj",
             "model.layers.53.self_attn.indexer*",
             "model.layers.53.self_attn.kv_a_proj_with_mqa",
             "model.layers.53.self_attn.kv_b_proj",
+            "model.layers.53.self_attn.o_proj",
             "model.layers.53.self_attn.q_a_proj",
             "model.layers.53.self_attn.q_b_proj",
             "model.layers.54.self_attn.indexer*",
             "model.layers.54.self_attn.kv_a_proj_with_mqa",
             "model.layers.54.self_attn.kv_b_proj",
+            "model.layers.54.self_attn.o_proj",
             "model.layers.54.self_attn.q_a_proj",
             "model.layers.54.self_attn.q_b_proj",
             "model.layers.55.self_attn.indexer*",
             "model.layers.55.self_attn.kv_a_proj_with_mqa",
             "model.layers.55.self_attn.kv_b_proj",
+            "model.layers.55.self_attn.o_proj",
             "model.layers.55.self_attn.q_a_proj",
             "model.layers.55.self_attn.q_b_proj",
             "model.layers.56.self_attn.indexer*",
             "model.layers.56.self_attn.kv_a_proj_with_mqa",
             "model.layers.56.self_attn.kv_b_proj",
+            "model.layers.56.self_attn.o_proj",
             "model.layers.56.self_attn.q_a_proj",
             "model.layers.56.self_attn.q_b_proj",
             "model.layers.57.self_attn.indexer*",
             "model.layers.57.self_attn.kv_a_proj_with_mqa",
             "model.layers.57.self_attn.kv_b_proj",
+            "model.layers.57.self_attn.o_proj",
             "model.layers.57.self_attn.q_a_proj",
             "model.layers.57.self_attn.q_b_proj",
             "model.layers.58.self_attn.indexer*",
             "model.layers.58.self_attn.kv_a_proj_with_mqa",
             "model.layers.58.self_attn.kv_b_proj",
+            "model.layers.58.self_attn.o_proj",
             "model.layers.58.self_attn.q_a_proj",
             "model.layers.58.self_attn.q_b_proj",
             "model.layers.59.self_attn.indexer*",
             "model.layers.59.self_attn.kv_a_proj_with_mqa",
             "model.layers.59.self_attn.kv_b_proj",
+            "model.layers.59.self_attn.o_proj",
             "model.layers.59.self_attn.q_a_proj",
             "model.layers.59.self_attn.q_b_proj",
             "model.layers.6.self_attn.indexer*",
             "model.layers.6.self_attn.kv_a_proj_with_mqa",
             "model.layers.6.self_attn.kv_b_proj",
+            "model.layers.6.self_attn.o_proj",
             "model.layers.6.self_attn.q_a_proj",
             "model.layers.6.self_attn.q_b_proj",
             "model.layers.60.self_attn.indexer*",
             "model.layers.60.self_attn.kv_a_proj_with_mqa",
             "model.layers.60.self_attn.kv_b_proj",
+            "model.layers.60.self_attn.o_proj",
             "model.layers.60.self_attn.q_a_proj",
             "model.layers.60.self_attn.q_b_proj",
             "model.layers.61.self_attn.indexer*",
             "model.layers.61.self_attn.kv_a_proj_with_mqa",
             "model.layers.61.self_attn.kv_b_proj",
+            "model.layers.61.self_attn.o_proj",
             "model.layers.61.self_attn.q_a_proj",
             "model.layers.61.self_attn.q_b_proj",
             "model.layers.62.self_attn.indexer*",
             "model.layers.62.self_attn.kv_a_proj_with_mqa",
             "model.layers.62.self_attn.kv_b_proj",
+            "model.layers.62.self_attn.o_proj",
             "model.layers.62.self_attn.q_a_proj",
             "model.layers.62.self_attn.q_b_proj",
             "model.layers.63.self_attn.indexer*",
             "model.layers.63.self_attn.kv_a_proj_with_mqa",
             "model.layers.63.self_attn.kv_b_proj",
+            "model.layers.63.self_attn.o_proj",
             "model.layers.63.self_attn.q_a_proj",
             "model.layers.63.self_attn.q_b_proj",
             "model.layers.64.self_attn.indexer*",
             "model.layers.64.self_attn.kv_a_proj_with_mqa",
             "model.layers.64.self_attn.kv_b_proj",
+            "model.layers.64.self_attn.o_proj",
             "model.layers.64.self_attn.q_a_proj",
             "model.layers.64.self_attn.q_b_proj",
             "model.layers.65.self_attn.indexer*",
             "model.layers.65.self_attn.kv_a_proj_with_mqa",
             "model.layers.65.self_attn.kv_b_proj",
+            "model.layers.65.self_attn.o_proj",
             "model.layers.65.self_attn.q_a_proj",
             "model.layers.65.self_attn.q_b_proj",
             "model.layers.66.self_attn.indexer*",
             "model.layers.66.self_attn.kv_a_proj_with_mqa",
             "model.layers.66.self_attn.kv_b_proj",
+            "model.layers.66.self_attn.o_proj",
             "model.layers.66.self_attn.q_a_proj",
             "model.layers.66.self_attn.q_b_proj",
             "model.layers.67.self_attn.indexer*",
             "model.layers.67.self_attn.kv_a_proj_with_mqa",
             "model.layers.67.self_attn.kv_b_proj",
+            "model.layers.67.self_attn.o_proj",
             "model.layers.67.self_attn.q_a_proj",
             "model.layers.67.self_attn.q_b_proj",
             "model.layers.68.self_attn.indexer*",
             "model.layers.68.self_attn.kv_a_proj_with_mqa",
             "model.layers.68.self_attn.kv_b_proj",
+            "model.layers.68.self_attn.o_proj",
             "model.layers.68.self_attn.q_a_proj",
             "model.layers.68.self_attn.q_b_proj",
             "model.layers.69.self_attn.indexer*",
             "model.layers.69.self_attn.kv_a_proj_with_mqa",
             "model.layers.69.self_attn.kv_b_proj",
+            "model.layers.69.self_attn.o_proj",
             "model.layers.69.self_attn.q_a_proj",
             "model.layers.69.self_attn.q_b_proj",
             "model.layers.7.self_attn.indexer*",
             "model.layers.7.self_attn.kv_a_proj_with_mqa",
             "model.layers.7.self_attn.kv_b_proj",
+            "model.layers.7.self_attn.o_proj",
             "model.layers.7.self_attn.q_a_proj",
             "model.layers.7.self_attn.q_b_proj",
             "model.layers.70.self_attn.indexer*",
             "model.layers.70.self_attn.kv_a_proj_with_mqa",
             "model.layers.70.self_attn.kv_b_proj",
+            "model.layers.70.self_attn.o_proj",
             "model.layers.70.self_attn.q_a_proj",
             "model.layers.70.self_attn.q_b_proj",
             "model.layers.71.self_attn.indexer*",
             "model.layers.71.self_attn.kv_a_proj_with_mqa",
             "model.layers.71.self_attn.kv_b_proj",
+            "model.layers.71.self_attn.o_proj",
             "model.layers.71.self_attn.q_a_proj",
             "model.layers.71.self_attn.q_b_proj",
             "model.layers.72.self_attn.indexer*",
             "model.layers.72.self_attn.kv_a_proj_with_mqa",
             "model.layers.72.self_attn.kv_b_proj",
+            "model.layers.72.self_attn.o_proj",
             "model.layers.72.self_attn.q_a_proj",
             "model.layers.72.self_attn.q_b_proj",
             "model.layers.73.self_attn.indexer*",
             "model.layers.73.self_attn.kv_a_proj_with_mqa",
             "model.layers.73.self_attn.kv_b_proj",
+            "model.layers.73.self_attn.o_proj",
             "model.layers.73.self_attn.q_a_proj",
             "model.layers.73.self_attn.q_b_proj",
             "model.layers.74.self_attn.indexer*",
             "model.layers.74.self_attn.kv_a_proj_with_mqa",
             "model.layers.74.self_attn.kv_b_proj",
+            "model.layers.74.self_attn.o_proj",
             "model.layers.74.self_attn.q_a_proj",
             "model.layers.74.self_attn.q_b_proj",
             "model.layers.75.self_attn.indexer*",
             "model.layers.75.self_attn.kv_a_proj_with_mqa",
             "model.layers.75.self_attn.kv_b_proj",
+            "model.layers.75.self_attn.o_proj",
             "model.layers.75.self_attn.q_a_proj",
             "model.layers.75.self_attn.q_b_proj",
             "model.layers.76.self_attn.indexer*",
             "model.layers.76.self_attn.kv_a_proj_with_mqa",
             "model.layers.76.self_attn.kv_b_proj",
+            "model.layers.76.self_attn.o_proj",
             "model.layers.76.self_attn.q_a_proj",
             "model.layers.76.self_attn.q_b_proj",
             "model.layers.77.self_attn.indexer*",
             "model.layers.77.self_attn.kv_a_proj_with_mqa",
             "model.layers.77.self_attn.kv_b_proj",
+            "model.layers.77.self_attn.o_proj",
             "model.layers.77.self_attn.q_a_proj",
             "model.layers.77.self_attn.q_b_proj",
+            "model.layers.78*",
+            "model.layers.78.self_attn.o_proj",
             "model.layers.8.self_attn.indexer*",
             "model.layers.8.self_attn.kv_a_proj_with_mqa",
             "model.layers.8.self_attn.kv_b_proj",
+            "model.layers.8.self_attn.o_proj",
             "model.layers.8.self_attn.q_a_proj",
             "model.layers.8.self_attn.q_b_proj",
             "model.layers.9.self_attn.indexer*",
             "model.layers.9.self_attn.kv_a_proj_with_mqa",
             "model.layers.9.self_attn.kv_b_proj",
+            "model.layers.9.self_attn.o_proj",
             "model.layers.9.self_attn.q_a_proj",
-            "model.layers.9.self_attn.q_b_proj",
-            "model.layers.78*"
+            "model.layers.9.self_attn.q_b_proj"
         ]
     }
 }

model-00001-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e4171aa409d3a946ae0b7fbec47bce0b5eadeaa2767f314495a55fd89682cf
-size 4402251280
+oid sha256:7870f036c5bbf68bb2bf9ae85e3062b8c2d02e8a8c7582128cbafa2bbdfbaf74
+size 4691657799

model-00005-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09588349af732d04bc53630b499420995df185fcd60e0ce3ee3e8d4f5bcc1c36
-size 1615853368
+oid sha256:2d6710a75ccb3500e1b619ef7f7d9932295b394e3d59548c884def8669d6441b
+size 1760568200

model-00009-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f3c6de94cdad5260031a289c2bcf4e846c858e449c9272d38beffa0a54c7f0
-size 1615853888
+oid sha256:481703e50de0d3a2655f187f6fcef48ac6d5e9c6fb15e15e0af6abc47e73e5e3
+size 1760568810

model-00013-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70e2de5453a6af08b3f3e9fcabff4a622f2e969570542218fb185ddcbfb3bc1
-size 1612706896
+oid sha256:ae94fbc9ab63791a374c7f49b1af0a2dfdb654f3365d52ccee4f39b33df8ed7d
+size 1757422112

model-00016-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291539225b6e2a3171fcd3dae9699af87c40294a3154da04e3230469ee74b2ef
-size 1615853320
+oid sha256:cfcfd515ab45876454d87548d94ffd75d170828e64ac143e59a43de8f181853b
+size 1760568122

model-00020-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f40fce50350e5c334c8593f52d8a05ea58a0f6545383cdc3c282847e8218c5a
-size 1615853792
+oid sha256:ba2d436fed871c7d8cad2b9dbe5ef57d1d9d1edddc726273e01a53305cef678e
+size 1760568758

model-00024-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7830693eef278334283a7036da0f68342c6f1da00e9d65731c4e62938e5a98fa
-size 1615854328
+oid sha256:12494386794c138b75db207ea82cfd880cc758bf88188be72dd6fbca96f511d3
+size 1760569014

model-00027-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bda713849d0e6a350e858d850066fb07d64f41f7b2a40e1c953fe4070eb844
-size 1615853280
+oid sha256:e93a008f80f0acfcf2fea14605963d10fc0f7bcb0fc313c0fa576bca336090e3
+size 1760568082

model-00031-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c20732d688cb1446d4b849a31954b25e638f85fb257ef1f34fa524868351032
-size 1615853696
+oid sha256:cbc27b8542c7b11c482a2041d676e668a215bf8e2b0ebb93f2e0ba2a487f3b3f
+size 1760568712

model-00035-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0602959a4ae6fed71ad813333064809ca26139a643b2d34640d3b79f9af5c2
-size 1615854224
+oid sha256:514e9311c64b28d1d83c19b841fd239bf253705ed7899ba852a5762ebba6ffdf
+size 1760568970

model-00038-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66aff8d25aaebe0c7394958236a192b3b03d322c0d7ca57a77309baec4f7ae2d
-size 1656886088
+oid sha256:e4c9851196e4e04ae8111fa4da5bc2f3bcb2ee4833f423bb7da31f8fc0a9f7f7
+size 1946302642

model-00042-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3e2e6d7c0c9561ad01b2c9420ac2335c51f16314a6ce50fcdf460dc28c62ccc
-size 1615853352
+oid sha256:e364dd72530abaf600c70a37a10de574cb15a0b56f61e8e2547e0e5dc4979e25
+size 1760568180

model-00046-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a4641350f675655b471bd64476979a0dcacfcfb6725893b81ceb87d005ceee
-size 1615853880
+oid sha256:ce35ccf277f912d487f2144bc0a890f15233b30b473efe0f2fc14b6ae5ff1c4c
+size 1760568802

model-00050-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0487c3cf587bf6f23d16f5a4866a6bfd77d123d51db2c924dc9171eb8b534d7b
-size 1612706920
+oid sha256:0910eec16d6f3f02f1cd68f9fef7af33442b99b87720be720d3845390641c763
+size 1757422132

model-00053-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:430f8132ec554b31b6fa3dea0f3dead3ff60f2157e6a11907cce9a549e3d29dc
-size 1615853304
+oid sha256:7e711c4b38d6725cacf5a2f6ecdb0441ff162994f46afa13203af3e75b5959d3
+size 1760568110

model-00057-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b34b013ecf37a92be2ac3b52a80cf5548ed1bc4892824c412762354f6180d00
-size 1615853784
+oid sha256:d076b4897f957896329a917853c17230f75dd8b5b2d113e9e64a0ef60b4bab7b
+size 1760568754

model-00061-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57fea288fe9424491f1784727d42c7056c755abadecdbea2332377bbee11b726
-size 1615854320
+oid sha256:723e1263803d35b3b4b1f839227e7100809c02ebda7c1d7cd24ee6ce8353394e
+size 1760569026

model-00064-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86de1afb566578fb56d58ebfb73ebfee958a49bb2fa1e470badbc0d56937eebb
-size 1615853272
+oid sha256:b87c41f145d23a0273c656a741ff0dbb707d163e32685641f9971892f91ffae4
+size 1760568074

model-00068-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4788d77df70197dbbf3dff2989762d98303822c9370937ed3d5ad10f24bf73bc
-size 1615853696
+oid sha256:c10b4ef8716d9c99e5813a5aa232f3a3d416e85d306389a81e49625d932101e4
+size 1760568704

model-00072-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00aae9a729d0e40579c8feacb3a76f5f4dbb8be3936236555d19113b859cf10
-size 1615854224
+oid sha256:ded765673bfbe3f957b34d425dc75648ca7695a6b24481a82f7bc5d519b0df7d
+size 1760568978

model-00075-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45f9b41dc169b76b2c3939b8c83323ad82f1f5a31732f22a0e75a6cf5a301cb
-size 1615853104
+oid sha256:9c288b84fefbaa3cb6b2b800f31d5c82c622ccbaf01134c9c15a49f8ffcb73ea
+size 1760567905

model-00079-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ccd71beff7103058d634d84ff2e652a281caf00339c7adadfb608eda4d29dbd
-size 1615853144
+oid sha256:36fc12ceb15bd974d4b312e307b8a5cbf8932f3a33ccaca5f66756ffa45d1212
+size 1760568123

model-00083-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98feec0434e77911d6b627b8a18302d339632c86d366013924601753b353a1f8
-size 1615854128
+oid sha256:d603b5f266eabdd2010871cc3f134ecf900ccaa15671d442644ededcf6218830
+size 1760568926

model-00086-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7e1407bed7a699211f6421912ce896bce3c5dd32bb9a9eeb4afc6d773df8a1
-size 1615853160
+oid sha256:20c26cd137651eabd61dc0c82cf05f9c06dd3fac94a702467897dc0b21c4b814
+size 1760567966

model-00090-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d94e93880de90147f94380e3a6649e1162883a122ec662119ab13ce84537846
-size 1615853480
+oid sha256:8a23e9edd6fae179cf2a054bcb85028f937c641c9bf60fd7b8b67361d1150f9c
+size 1760568414

model-00094-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb19bffd99c69e63cb168a5f322668d5bf8882ba6f09b247bae6ab3f26dbda9f
-size 1615854032
+oid sha256:308a55b7d43ee96827533e8b7f7dfc2df3ebc659f139f1c88337b2d01b7b736d
+size 1760568878

model-00097-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ecf99d7de2d1725af448c4f0e867303448859ed645a9a19ec0c628f6a9d44e
-size 1615853152
+oid sha256:37abfca35a8946a6e711ae8b630af1308f3b832ec99ceae2a577faf074abb1b3
+size 1760567954

model-00101-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906848f59c529d010b159adecf3dd0604e322dcce4592f89edf64a7497c016b9
-size 1615853400
+oid sha256:62bfd93c56c0a0edb8374fa3bf776206b31317274fd35062dfdebb54e65c5a52
+size 1760568282

model-00105-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e15b04798591957b1288c389e398733814b6d6de898fa04a799653221f70d4
-size 1615853944
+oid sha256:ab48c343adf29718d1d7ff58784ab967180fccc4fb3be0c70d258fdefe6f9abe
+size 1760568842

model-00109-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56b87de1a3829d4330720b6e47048d0f6c10f1fc13eaa777fe0342b2f94ddfa
-size 1571667424
+oid sha256:d295676a9fce9696e93964b2b2650b026a15c1c2d5a01539b69f314bea6eaca8
+size 1716382675

model-00112-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae565c54d333be21da69708ceb591a964cdf1ca5b96760a74e197dd673bd0572
-size 1615853328
+oid sha256:6390eea1472199059bb900825edbcfc85560f68d72764043a4d67a00738767c5
+size 1760568134

model-00116-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ae23b5488c48453b8440cc33f5b1c32721b9ea7a99d265b7ccc01b049267f0
-size 1615853328
+oid sha256:cac4e061584b91890d20cbd138192c5ba27a02ec7dd8b27e174d7f5282d05fc2
+size 1760568281

model-00120-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eabc05e4eb32652fdbd202fdd1fab9ba03820757d7b1469868d4c54b6c3a60f
-size 1615854304
+oid sha256:d178e78532187be4612d2744ed7e53d822ce8afa82b4af506aa856720a498341
+size 1760568989

model-00123-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a0be1a9fa62ddf0c840ce92c17164660c157502a3e9da37d075b2d9dbeb5ae0
-size 1615853280
+oid sha256:40a05abc6946ad1129122db2d03cc133b0ba0e25a18c9979301ab416c07c8954
+size 1760568086

model-00127-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b5755180a5c1a7b4715c8d559d17aa070c08759d54618558fe9d42befa11e2
-size 1615853720
+oid sha256:f33c44ebf0e2dbda7c6cec7472628f676e6374fc393b364696715210cafff1c0
+size 1760568722

model-00131-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6dbf1621142e10c25a420eaa599881db1fc0da8b6a835599af3752e2b25e52d
-size 1615854248
+oid sha256:f3267e982b412928d9d8661fbab0dd1ec93eb3d6329bcbbe323b79551ef05760
+size 1760568982

model-00134-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028906387332b35e94c08bc80876b3cc49ac6d2b3ca476101bf48ba786a43635
-size 1615853232
+oid sha256:2900fe1bc2049410d2bf850ec90f4187292af5a399fa83386844d5fad031d97f
+size 1760568038

model-00138-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ce35e51ae46569dd73ce69da82390f5318b2cf4a6ce1430388b87aa6636a2d
-size 1615853624
+oid sha256:ff3800bcf6e7d8266ff6b6da43e27ee55a2b6bf5e7937e4acfb6edd052923bcc
+size 1760568604

model-00142-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f221149878b537338550759f672caac8e5ce88f8a20c7b9757f77f8427877fd
-size 1615854160
+oid sha256:649943b6ed8b6f04584122931e1718b6a2c38f790b225e06eebf9b86b0529289
+size 1760568942

model-00145-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c50aedd081c34edd70dbb901334bde04ba8ddecbafaeaa350f9329f5f7244a9a
-size 1615853184
+oid sha256:34b1d41e22f86a07815f3ab6a3ba972a5f2c1fba79016f56aa868d0e37d4e525
+size 1760567990

model-00149-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab65cfad9d99b855c85a24ef86018deb87cf797201871ba2fe47e30a357cb48
-size 1615853512
+oid sha256:01b0876316e0e3152e81c399f49ea205ad8bb28d33dacf7a75a7645d8bcaf54a
+size 1760568462

model-00153-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40a6fc5a454e57944e77abd42044ab8466b88b448f7ba248f30b456374a6e4a
-size 1615854056
+oid sha256:3c7f25216837ffd318db5a60405614a2c2f9eb30c7f55134f5aeff6568d6475e
+size 1760568886

model-00156-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:050fa8dc6d99439897c1d65adf79e948f8334ee656003fb845ed0d3109425b08
-size 1615853120
+oid sha256:8bc9c3e9f9f6ce1c85edde86b671cfe4d7627fabf9d41ac8fb55b68d909abad9
+size 1760567921

model-00160-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c8a76cde6457f6f7f427acaef613afac6886b25272750d153f49f53fbdafa9
-size 1615852904
+oid sha256:6112fe4fb6e0f815132fcb687a7e4fe351c69ebb310e2042821d209547af5925
+size 1760567807

model-00164-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b440ed631c06e45b41c33525b9f28ce7e287a17fd77984f01b518fa7b38b1cc3
-size 1615853960
+oid sha256:95dbe66aae435181b34f55587c63e706924d7f7a1a801c6c2fdbd4b3390736cb
+size 1760568838

model-00168-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c493f1f9d4a2282225182024ae62913878ad4fc975eac110bf9bf79fa5e68bf8
-size 1571667424
+oid sha256:54c8e055f26c5d5df30cefd768c8d266825ece9bf579dcef5bbabcdbd65907a0
+size 1716382675

model-00171-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4c4a0905971342ad98bb4a01bc749194f55638fcf7280ddf52f8470daa3ace
-size 1615853328
+oid sha256:90b6b2b75a9ab33b1abe311503ace9fc02d3cc6c5a73a8506837f8db2c5be50f
+size 1760568134

model-00175-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deacb06367c4bf7018e3fd8b77f83191c2b6d81bbbb589cc6b7e0610fa3baaf4
-size 1615853816
+oid sha256:161abac9ccbeb5410458123c09936bb155fbb4aa1ef893b2a860f84b3066e932
+size 1760568770