Upload folder using huggingface_hub

config.json

@@ -96,7 +96,7 @@
           "dynamic": false,
           "group_size": 32,
           "num_bits": 4,
-          "observer": "minmax",
+          "observer": "mse",
           "observer_kwargs": {},
           "strategy": "group",
           "symmetric": true,
@@ -111,205 +111,397 @@
       "model.layers.0.linear_attn.in_proj_ba",
       "model.layers.0.linear_attn.out_proj",
       "model.layers.0.mlp.gate",
+      "model.layers.0.mlp.shared_expert.gate_proj",
+      "model.layers.0.mlp.shared_expert.up_proj",
+      "model.layers.0.mlp.shared_expert.down_proj",
       "model.layers.0.mlp.shared_expert_gate",
       "model.layers.1.linear_attn.in_proj_qkvz",
       "model.layers.1.linear_attn.in_proj_ba",
       "model.layers.1.linear_attn.out_proj",
       "model.layers.1.mlp.gate",
+      "model.layers.1.mlp.shared_expert.gate_proj",
+      "model.layers.1.mlp.shared_expert.up_proj",
+      "model.layers.1.mlp.shared_expert.down_proj",
       "model.layers.1.mlp.shared_expert_gate",
       "model.layers.2.linear_attn.in_proj_qkvz",
       "model.layers.2.linear_attn.in_proj_ba",
       "model.layers.2.linear_attn.out_proj",
       "model.layers.2.mlp.gate",
+      "model.layers.2.mlp.shared_expert.gate_proj",
+      "model.layers.2.mlp.shared_expert.up_proj",
+      "model.layers.2.mlp.shared_expert.down_proj",
       "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.3.self_attn.q_proj",
+      "model.layers.3.self_attn.k_proj",
+      "model.layers.3.self_attn.v_proj",
+      "model.layers.3.self_attn.o_proj",
       "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.shared_expert.gate_proj",
+      "model.layers.3.mlp.shared_expert.up_proj",
+      "model.layers.3.mlp.shared_expert.down_proj",
       "model.layers.3.mlp.shared_expert_gate",
       "model.layers.4.linear_attn.in_proj_qkvz",
       "model.layers.4.linear_attn.in_proj_ba",
       "model.layers.4.linear_attn.out_proj",
       "model.layers.4.mlp.gate",
+      "model.layers.4.mlp.shared_expert.gate_proj",
+      "model.layers.4.mlp.shared_expert.up_proj",
+      "model.layers.4.mlp.shared_expert.down_proj",
       "model.layers.4.mlp.shared_expert_gate",
       "model.layers.5.linear_attn.in_proj_qkvz",
       "model.layers.5.linear_attn.in_proj_ba",
       "model.layers.5.linear_attn.out_proj",
       "model.layers.5.mlp.gate",
+      "model.layers.5.mlp.shared_expert.gate_proj",
+      "model.layers.5.mlp.shared_expert.up_proj",
+      "model.layers.5.mlp.shared_expert.down_proj",
       "model.layers.5.mlp.shared_expert_gate",
       "model.layers.6.linear_attn.in_proj_qkvz",
       "model.layers.6.linear_attn.in_proj_ba",
       "model.layers.6.linear_attn.out_proj",
       "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.shared_expert.gate_proj",
+      "model.layers.6.mlp.shared_expert.up_proj",
+      "model.layers.6.mlp.shared_expert.down_proj",
       "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.7.self_attn.q_proj",
+      "model.layers.7.self_attn.k_proj",
+      "model.layers.7.self_attn.v_proj",
+      "model.layers.7.self_attn.o_proj",
       "model.layers.7.mlp.gate",
+      "model.layers.7.mlp.shared_expert.gate_proj",
+      "model.layers.7.mlp.shared_expert.up_proj",
+      "model.layers.7.mlp.shared_expert.down_proj",
       "model.layers.7.mlp.shared_expert_gate",
       "model.layers.8.linear_attn.in_proj_qkvz",
       "model.layers.8.linear_attn.in_proj_ba",
       "model.layers.8.linear_attn.out_proj",
       "model.layers.8.mlp.gate",
+      "model.layers.8.mlp.shared_expert.gate_proj",
+      "model.layers.8.mlp.shared_expert.up_proj",
+      "model.layers.8.mlp.shared_expert.down_proj",
       "model.layers.8.mlp.shared_expert_gate",
       "model.layers.9.linear_attn.in_proj_qkvz",
       "model.layers.9.linear_attn.in_proj_ba",
       "model.layers.9.linear_attn.out_proj",
       "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.shared_expert.gate_proj",
+      "model.layers.9.mlp.shared_expert.up_proj",
+      "model.layers.9.mlp.shared_expert.down_proj",
       "model.layers.9.mlp.shared_expert_gate",
       "model.layers.10.linear_attn.in_proj_qkvz",
       "model.layers.10.linear_attn.in_proj_ba",
       "model.layers.10.linear_attn.out_proj",
       "model.layers.10.mlp.gate",
+      "model.layers.10.mlp.shared_expert.gate_proj",
+      "model.layers.10.mlp.shared_expert.up_proj",
+      "model.layers.10.mlp.shared_expert.down_proj",
       "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.11.self_attn.q_proj",
+      "model.layers.11.self_attn.k_proj",
+      "model.layers.11.self_attn.v_proj",
+      "model.layers.11.self_attn.o_proj",
       "model.layers.11.mlp.gate",
+      "model.layers.11.mlp.shared_expert.gate_proj",
+      "model.layers.11.mlp.shared_expert.up_proj",
+      "model.layers.11.mlp.shared_expert.down_proj",
       "model.layers.11.mlp.shared_expert_gate",
       "model.layers.12.linear_attn.in_proj_qkvz",
       "model.layers.12.linear_attn.in_proj_ba",
       "model.layers.12.linear_attn.out_proj",
       "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.shared_expert.gate_proj",
+      "model.layers.12.mlp.shared_expert.up_proj",
+      "model.layers.12.mlp.shared_expert.down_proj",
       "model.layers.12.mlp.shared_expert_gate",
       "model.layers.13.linear_attn.in_proj_qkvz",
       "model.layers.13.linear_attn.in_proj_ba",
       "model.layers.13.linear_attn.out_proj",
       "model.layers.13.mlp.gate",
+      "model.layers.13.mlp.shared_expert.gate_proj",
+      "model.layers.13.mlp.shared_expert.up_proj",
+      "model.layers.13.mlp.shared_expert.down_proj",
       "model.layers.13.mlp.shared_expert_gate",
       "model.layers.14.linear_attn.in_proj_qkvz",
       "model.layers.14.linear_attn.in_proj_ba",
       "model.layers.14.linear_attn.out_proj",
       "model.layers.14.mlp.gate",
+      "model.layers.14.mlp.shared_expert.gate_proj",
+      "model.layers.14.mlp.shared_expert.up_proj",
+      "model.layers.14.mlp.shared_expert.down_proj",
       "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.15.self_attn.q_proj",
+      "model.layers.15.self_attn.k_proj",
+      "model.layers.15.self_attn.v_proj",
+      "model.layers.15.self_attn.o_proj",
       "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.shared_expert.gate_proj",
+      "model.layers.15.mlp.shared_expert.up_proj",
+      "model.layers.15.mlp.shared_expert.down_proj",
       "model.layers.15.mlp.shared_expert_gate",
       "model.layers.16.linear_attn.in_proj_qkvz",
       "model.layers.16.linear_attn.in_proj_ba",
       "model.layers.16.linear_attn.out_proj",
       "model.layers.16.mlp.gate",
+      "model.layers.16.mlp.shared_expert.gate_proj",
+      "model.layers.16.mlp.shared_expert.up_proj",
+      "model.layers.16.mlp.shared_expert.down_proj",
       "model.layers.16.mlp.shared_expert_gate",
       "model.layers.17.linear_attn.in_proj_qkvz",
       "model.layers.17.linear_attn.in_proj_ba",
       "model.layers.17.linear_attn.out_proj",
       "model.layers.17.mlp.gate",
+      "model.layers.17.mlp.shared_expert.gate_proj",
+      "model.layers.17.mlp.shared_expert.up_proj",
+      "model.layers.17.mlp.shared_expert.down_proj",
       "model.layers.17.mlp.shared_expert_gate",
       "model.layers.18.linear_attn.in_proj_qkvz",
       "model.layers.18.linear_attn.in_proj_ba",
       "model.layers.18.linear_attn.out_proj",
       "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.shared_expert.gate_proj",
+      "model.layers.18.mlp.shared_expert.up_proj",
+      "model.layers.18.mlp.shared_expert.down_proj",
       "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.19.self_attn.q_proj",
+      "model.layers.19.self_attn.k_proj",
+      "model.layers.19.self_attn.v_proj",
+      "model.layers.19.self_attn.o_proj",
       "model.layers.19.mlp.gate",
+      "model.layers.19.mlp.shared_expert.gate_proj",
+      "model.layers.19.mlp.shared_expert.up_proj",
+      "model.layers.19.mlp.shared_expert.down_proj",
       "model.layers.19.mlp.shared_expert_gate",
       "model.layers.20.linear_attn.in_proj_qkvz",
       "model.layers.20.linear_attn.in_proj_ba",
       "model.layers.20.linear_attn.out_proj",
       "model.layers.20.mlp.gate",
+      "model.layers.20.mlp.shared_expert.gate_proj",
+      "model.layers.20.mlp.shared_expert.up_proj",
+      "model.layers.20.mlp.shared_expert.down_proj",
       "model.layers.20.mlp.shared_expert_gate",
       "model.layers.21.linear_attn.in_proj_qkvz",
       "model.layers.21.linear_attn.in_proj_ba",
       "model.layers.21.linear_attn.out_proj",
       "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.shared_expert.gate_proj",
+      "model.layers.21.mlp.shared_expert.up_proj",
+      "model.layers.21.mlp.shared_expert.down_proj",
       "model.layers.21.mlp.shared_expert_gate",
       "model.layers.22.linear_attn.in_proj_qkvz",
       "model.layers.22.linear_attn.in_proj_ba",
       "model.layers.22.linear_attn.out_proj",
       "model.layers.22.mlp.gate",
+      "model.layers.22.mlp.shared_expert.gate_proj",
+      "model.layers.22.mlp.shared_expert.up_proj",
+      "model.layers.22.mlp.shared_expert.down_proj",
       "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.23.self_attn.q_proj",
+      "model.layers.23.self_attn.k_proj",
+      "model.layers.23.self_attn.v_proj",
+      "model.layers.23.self_attn.o_proj",
       "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.shared_expert.gate_proj",
+      "model.layers.23.mlp.shared_expert.up_proj",
+      "model.layers.23.mlp.shared_expert.down_proj",
       "model.layers.23.mlp.shared_expert_gate",
       "model.layers.24.linear_attn.in_proj_qkvz",
       "model.layers.24.linear_attn.in_proj_ba",
       "model.layers.24.linear_attn.out_proj",
       "model.layers.24.mlp.gate",
+      "model.layers.24.mlp.shared_expert.gate_proj",
+      "model.layers.24.mlp.shared_expert.up_proj",
+      "model.layers.24.mlp.shared_expert.down_proj",
       "model.layers.24.mlp.shared_expert_gate",
       "model.layers.25.linear_attn.in_proj_qkvz",
       "model.layers.25.linear_attn.in_proj_ba",
       "model.layers.25.linear_attn.out_proj",
       "model.layers.25.mlp.gate",
+      "model.layers.25.mlp.shared_expert.gate_proj",
+      "model.layers.25.mlp.shared_expert.up_proj",
+      "model.layers.25.mlp.shared_expert.down_proj",
       "model.layers.25.mlp.shared_expert_gate",
       "model.layers.26.linear_attn.in_proj_qkvz",
       "model.layers.26.linear_attn.in_proj_ba",
       "model.layers.26.linear_attn.out_proj",
       "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.shared_expert.gate_proj",
+      "model.layers.26.mlp.shared_expert.up_proj",
+      "model.layers.26.mlp.shared_expert.down_proj",
       "model.layers.26.mlp.shared_expert_gate",
+      "model.layers.27.self_attn.q_proj",
+      "model.layers.27.self_attn.k_proj",
+      "model.layers.27.self_attn.v_proj",
+      "model.layers.27.self_attn.o_proj",
       "model.layers.27.mlp.gate",
+      "model.layers.27.mlp.shared_expert.gate_proj",
+      "model.layers.27.mlp.shared_expert.up_proj",
+      "model.layers.27.mlp.shared_expert.down_proj",
       "model.layers.27.mlp.shared_expert_gate",
       "model.layers.28.linear_attn.in_proj_qkvz",
       "model.layers.28.linear_attn.in_proj_ba",
       "model.layers.28.linear_attn.out_proj",
       "model.layers.28.mlp.gate",
+      "model.layers.28.mlp.shared_expert.gate_proj",
+      "model.layers.28.mlp.shared_expert.up_proj",
+      "model.layers.28.mlp.shared_expert.down_proj",
       "model.layers.28.mlp.shared_expert_gate",
       "model.layers.29.linear_attn.in_proj_qkvz",
       "model.layers.29.linear_attn.in_proj_ba",
       "model.layers.29.linear_attn.out_proj",
       "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.shared_expert.gate_proj",
+      "model.layers.29.mlp.shared_expert.up_proj",
+      "model.layers.29.mlp.shared_expert.down_proj",
       "model.layers.29.mlp.shared_expert_gate",
       "model.layers.30.linear_attn.in_proj_qkvz",
       "model.layers.30.linear_attn.in_proj_ba",
       "model.layers.30.linear_attn.out_proj",
       "model.layers.30.mlp.gate",
+      "model.layers.30.mlp.shared_expert.gate_proj",
+      "model.layers.30.mlp.shared_expert.up_proj",
+      "model.layers.30.mlp.shared_expert.down_proj",
       "model.layers.30.mlp.shared_expert_gate",
+      "model.layers.31.self_attn.q_proj",
+      "model.layers.31.self_attn.k_proj",
+      "model.layers.31.self_attn.v_proj",
+      "model.layers.31.self_attn.o_proj",
       "model.layers.31.mlp.gate",
+      "model.layers.31.mlp.shared_expert.gate_proj",
+      "model.layers.31.mlp.shared_expert.up_proj",
+      "model.layers.31.mlp.shared_expert.down_proj",
       "model.layers.31.mlp.shared_expert_gate",
       "model.layers.32.linear_attn.in_proj_qkvz",
       "model.layers.32.linear_attn.in_proj_ba",
       "model.layers.32.linear_attn.out_proj",
       "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.shared_expert.gate_proj",
+      "model.layers.32.mlp.shared_expert.up_proj",
+      "model.layers.32.mlp.shared_expert.down_proj",
       "model.layers.32.mlp.shared_expert_gate",
       "model.layers.33.linear_attn.in_proj_qkvz",
       "model.layers.33.linear_attn.in_proj_ba",
       "model.layers.33.linear_attn.out_proj",
       "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.shared_expert.gate_proj",
+      "model.layers.33.mlp.shared_expert.up_proj",
+      "model.layers.33.mlp.shared_expert.down_proj",
       "model.layers.33.mlp.shared_expert_gate",
       "model.layers.34.linear_attn.in_proj_qkvz",
       "model.layers.34.linear_attn.in_proj_ba",
       "model.layers.34.linear_attn.out_proj",
       "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.shared_expert.gate_proj",
+      "model.layers.34.mlp.shared_expert.up_proj",
+      "model.layers.34.mlp.shared_expert.down_proj",
       "model.layers.34.mlp.shared_expert_gate",
+      "model.layers.35.self_attn.q_proj",
+      "model.layers.35.self_attn.k_proj",
+      "model.layers.35.self_attn.v_proj",
+      "model.layers.35.self_attn.o_proj",
       "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.shared_expert.gate_proj",
+      "model.layers.35.mlp.shared_expert.up_proj",
+      "model.layers.35.mlp.shared_expert.down_proj",
       "model.layers.35.mlp.shared_expert_gate",
       "model.layers.36.linear_attn.in_proj_qkvz",
       "model.layers.36.linear_attn.in_proj_ba",
       "model.layers.36.linear_attn.out_proj",
       "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.shared_expert.gate_proj",
+      "model.layers.36.mlp.shared_expert.up_proj",
+      "model.layers.36.mlp.shared_expert.down_proj",
       "model.layers.36.mlp.shared_expert_gate",
       "model.layers.37.linear_attn.in_proj_qkvz",
       "model.layers.37.linear_attn.in_proj_ba",
       "model.layers.37.linear_attn.out_proj",
       "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.shared_expert.gate_proj",
+      "model.layers.37.mlp.shared_expert.up_proj",
+      "model.layers.37.mlp.shared_expert.down_proj",
       "model.layers.37.mlp.shared_expert_gate",
       "model.layers.38.linear_attn.in_proj_qkvz",
       "model.layers.38.linear_attn.in_proj_ba",
       "model.layers.38.linear_attn.out_proj",
       "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.shared_expert.gate_proj",
+      "model.layers.38.mlp.shared_expert.up_proj",
+      "model.layers.38.mlp.shared_expert.down_proj",
       "model.layers.38.mlp.shared_expert_gate",
+      "model.layers.39.self_attn.q_proj",
+      "model.layers.39.self_attn.k_proj",
+      "model.layers.39.self_attn.v_proj",
+      "model.layers.39.self_attn.o_proj",
       "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.shared_expert.gate_proj",
+      "model.layers.39.mlp.shared_expert.up_proj",
+      "model.layers.39.mlp.shared_expert.down_proj",
       "model.layers.39.mlp.shared_expert_gate",
       "model.layers.40.linear_attn.in_proj_qkvz",
       "model.layers.40.linear_attn.in_proj_ba",
       "model.layers.40.linear_attn.out_proj",
       "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.shared_expert.gate_proj",
+      "model.layers.40.mlp.shared_expert.up_proj",
+      "model.layers.40.mlp.shared_expert.down_proj",
       "model.layers.40.mlp.shared_expert_gate",
       "model.layers.41.linear_attn.in_proj_qkvz",
       "model.layers.41.linear_attn.in_proj_ba",
       "model.layers.41.linear_attn.out_proj",
       "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.shared_expert.gate_proj",
+      "model.layers.41.mlp.shared_expert.up_proj",
+      "model.layers.41.mlp.shared_expert.down_proj",
       "model.layers.41.mlp.shared_expert_gate",
       "model.layers.42.linear_attn.in_proj_qkvz",
       "model.layers.42.linear_attn.in_proj_ba",
       "model.layers.42.linear_attn.out_proj",
       "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.shared_expert.gate_proj",
+      "model.layers.42.mlp.shared_expert.up_proj",
+      "model.layers.42.mlp.shared_expert.down_proj",
       "model.layers.42.mlp.shared_expert_gate",
+      "model.layers.43.self_attn.q_proj",
+      "model.layers.43.self_attn.k_proj",
+      "model.layers.43.self_attn.v_proj",
+      "model.layers.43.self_attn.o_proj",
       "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.shared_expert.gate_proj",
+      "model.layers.43.mlp.shared_expert.up_proj",
+      "model.layers.43.mlp.shared_expert.down_proj",
       "model.layers.43.mlp.shared_expert_gate",
       "model.layers.44.linear_attn.in_proj_qkvz",
       "model.layers.44.linear_attn.in_proj_ba",
       "model.layers.44.linear_attn.out_proj",
       "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.shared_expert.gate_proj",
+      "model.layers.44.mlp.shared_expert.up_proj",
+      "model.layers.44.mlp.shared_expert.down_proj",
       "model.layers.44.mlp.shared_expert_gate",
       "model.layers.45.linear_attn.in_proj_qkvz",
       "model.layers.45.linear_attn.in_proj_ba",
       "model.layers.45.linear_attn.out_proj",
       "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.shared_expert.gate_proj",
+      "model.layers.45.mlp.shared_expert.up_proj",
+      "model.layers.45.mlp.shared_expert.down_proj",
       "model.layers.45.mlp.shared_expert_gate",
       "model.layers.46.linear_attn.in_proj_qkvz",
       "model.layers.46.linear_attn.in_proj_ba",
       "model.layers.46.linear_attn.out_proj",
       "model.layers.46.mlp.gate",
+      "model.layers.46.mlp.shared_expert.gate_proj",
+      "model.layers.46.mlp.shared_expert.up_proj",
+      "model.layers.46.mlp.shared_expert.down_proj",
       "model.layers.46.mlp.shared_expert_gate",
+      "model.layers.47.self_attn.q_proj",
+      "model.layers.47.self_attn.k_proj",
+      "model.layers.47.self_attn.v_proj",
+      "model.layers.47.self_attn.o_proj",
       "model.layers.47.mlp.gate",
+      "model.layers.47.mlp.shared_expert.gate_proj",
+      "model.layers.47.mlp.shared_expert.up_proj",
+      "model.layers.47.mlp.shared_expert.down_proj",
       "model.layers.47.mlp.shared_expert_gate",
       "lm_head"
     ],
@@ -318,7 +510,7 @@
     "quantization_status": "compressed",
     "sparsity_config": {},
     "transform_config": {},
-    "version": "0.11.0"
+    "version": "0.11.1.a20250912"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

model-00001-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6135a19f254eebd8f3d2394fd9d50d80326dcdfdcb8c312112ba2b1e42cd3f
-size 5002202400
+oid sha256:b123302346e0c1a953599b3e4848b9238410aa78c5ec078a8780c0b92e6166c3
+size 5002226064

model-00002-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa395cb1aad3c427e48b827590340d894af8773e3b703255fc25ae1d88a07083
-size 5002558984
+oid sha256:66a0e5064cbf8850c0911131269abdf7f49c3e0c539ef290ce13513dc5be683d
+size 5002906536

model-00003-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cff4f0a8c8510b729c92c9757ebd66f1b60a83e874b81d6eac1fd941b96ff7a
-size 5002581480
+oid sha256:4facabf40f7f02c06778a220a358a363a6fc22fb742b9b388edd951cefc2859d
+size 5002469472

model-00004-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb589fb3c579a054305a1f53a7f5a195a119a12be3b8d7c90f655bb8c9b243a3
-size 5002914632
+oid sha256:c029eb5c11d18b2183b92c5659bc9302d5c054aea9d2f384988def44209a37fe
+size 5002480424

model-00005-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0658cd17d934497288bf7eb0824a36ea362a9f3a11fdc4fcf04acbdafa06aa4a
-size 5002582176
+oid sha256:96ec33e8153f4fe978b422eed68f1ce1ad39258f9ca820d5cb97f9d87b88230f
+size 5002930176

model-00006-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3672fb6b070435c487bce0f91e6c7917e4bc3e5e37607788c5920f74b1064ee
-size 5002582968
+oid sha256:07b8256cf1e3ec255bf915f5969722a9ac602acbf030b5eb75eb7d86ba610558
+size 4991135440

model-00007-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcbf8b50036ea448bd0742658d33cbf390b9ae6df167fe78931536ea0d5ace6e
-size 5002946736
+oid sha256:27c0e4ac72340dea5c44fe9f9448926eed3e5037ecf7e868436d7a9e8664b65c
+size 5002894032

model-00008-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8350739c18d519126b05cc53737bb22d0615c2c0d9136615c82d1873e3216fec
-size 5002648768
+oid sha256:7d81372dfdc7193d189011d9cc4c541df1434cd5a9141149de9861829924932c
+size 5002929656

model-00009-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041d58c26c913cc8c3c9839e711830b773f841b927fe043ef66b37929016f6e0
-size 5002582968
+oid sha256:698343c0b33ccc335b7838eee4816cded3aec63ecbd96e48e831e95fd32c9c5f
+size 5002471416

model-00010-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445460ac907283adb4cff55a8b53f6dde81742ed3b2ba3b6b8ab35ff236a4dfc
-size 2534274448
+oid sha256:b4cf5cf95d61c3837c0e23834c73a33843a1deec8a873671b45f82be5b6933c6
+size 3232720920

model.safetensors.index.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7260428d31ae24ba1bee018b10ca08d05f7bf68dc13ab2619854e1f6c23aba
-size 21604155
+oid sha256:7de3074ca86e26d7798358028f7e09b856066ab3b0f6b76ce120b209dc1cd25d
+size 21565735

recipe.yaml

@@ -1,5 +1,5 @@
-quant_stage:
-  quant_modifiers:
+default_stage:
+  default_modifiers:
     AWQModifier:
       config_groups:
         group_0:
@@ -13,15 +13,16 @@ quant_stage:
             block_structure: null
             dynamic: false
             actorder: null
-            observer: minmax
+            observer: mse
             observer_kwargs: {}
           input_activations: null
           output_activations: null
           format: null
       targets: [Linear]
-      ignore: [lm_head, model.embed_tokens, 're:mtp.*', 're:.*input_layernorm$', 're:.*post_attention_layernorm$',
-        model.norm, 're:.*mlp[.]gate$', 're:.*shared_expert_gate$', 're:.*linear_attn.*',
-        're:.*norm$', 're:.*rotary_emb.*', 're:.*q_norm$', 're:.*k_norm$']
+      ignore: [model.embed_tokens, 're:.*input_layernorm$', 're:.*linear_attn.*', 're:.*norm.*',
+        're:.*RMSNorm.*', 're:.*rotary.*', 're:.*shared_expert.*', 're:.*shared_expert_gate$',
+        're:.*mlp[.]gate$', 're:.*router.*', 're:.*post_attention_layernorm$', 're:.*self_attn.*',
+        're:mtp.*', lm_head]
       mappings:
       - smooth_layer: re:.*input_layernorm$
         balance_layers: ['re:.*self_attn[.]q_proj$', 're:.*self_attn[.]k_proj$', 're:.*self_attn[.]v_proj$',
@@ -32,4 +33,6 @@ quant_stage:
         balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
       - smooth_layer: re:.*up_proj$
         balance_layers: ['re:.*down_proj$']
+      - smooth_layer: re:.*linear_attn[.]norm$
+        balance_layers: ['re:.*linear_attn[.]out_proj$']
       duo_scaling: true

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1a036a9837df9caeebb840d09d80e8feef0f6d2bae982970d1ad34f5946aff
-size 11422753
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654