Upload folder using huggingface_hub

chat_template.jinja

@@ -32,10 +32,10 @@ For each function call, output the function name and arguments within the follow
 {%- set ns = namespace(last_user_index=-1) %}
 {%- for m in messages %}
     {%- if m.role == 'user' %}
-        {% set ns.last_user_index = loop.index0 -%}
+        {%- set ns.last_user_index = loop.index0 -%}
     {%- endif %}
 {%- endfor %}
-{% for m in messages %}
+{%- for m in messages -%}
 {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
 {%- elif m.role == 'assistant' -%}
 <|assistant|>

config.json

@@ -64,6 +64,7 @@
                 "qscheme": "per_group",
                 "ch_axis": -1,
                 "group_size": 32,
+                "block_size": null,
                 "symmetric": null,
                 "round_method": "half_even",
                 "scale_type": "float",
@@ -80,6 +81,7 @@
                 "qscheme": "per_group",
                 "ch_axis": -1,
                 "group_size": 32,
+                "block_size": null,
                 "symmetric": null,
                 "round_method": "half_even",
                 "scale_type": "float",
@@ -117,9 +119,6 @@
             "model.layers.1.self_attn.q_a_proj",
             "model.layers.1.self_attn.q_b_proj",
             "model.layers.10.mlp.gate",
-            "model.layers.10.mlp.shared_experts.down_proj",
-            "model.layers.10.mlp.shared_experts.gate_proj",
-            "model.layers.10.mlp.shared_experts.up_proj",
             "model.layers.10.self_attn.indexer.weights_proj",
             "model.layers.10.self_attn.indexer.wk",
             "model.layers.10.self_attn.indexer.wq_b",
@@ -129,9 +128,6 @@
             "model.layers.10.self_attn.q_a_proj",
             "model.layers.10.self_attn.q_b_proj",
             "model.layers.11.mlp.gate",
-            "model.layers.11.mlp.shared_experts.down_proj",
-            "model.layers.11.mlp.shared_experts.gate_proj",
-            "model.layers.11.mlp.shared_experts.up_proj",
             "model.layers.11.self_attn.indexer.weights_proj",
             "model.layers.11.self_attn.indexer.wk",
             "model.layers.11.self_attn.indexer.wq_b",
@@ -141,9 +137,6 @@
             "model.layers.11.self_attn.q_a_proj",
             "model.layers.11.self_attn.q_b_proj",
             "model.layers.12.mlp.gate",
-            "model.layers.12.mlp.shared_experts.down_proj",
-            "model.layers.12.mlp.shared_experts.gate_proj",
-            "model.layers.12.mlp.shared_experts.up_proj",
             "model.layers.12.self_attn.indexer.weights_proj",
             "model.layers.12.self_attn.indexer.wk",
             "model.layers.12.self_attn.indexer.wq_b",
@@ -153,9 +146,6 @@
             "model.layers.12.self_attn.q_a_proj",
             "model.layers.12.self_attn.q_b_proj",
             "model.layers.13.mlp.gate",
-            "model.layers.13.mlp.shared_experts.down_proj",
-            "model.layers.13.mlp.shared_experts.gate_proj",
-            "model.layers.13.mlp.shared_experts.up_proj",
             "model.layers.13.self_attn.indexer.weights_proj",
             "model.layers.13.self_attn.indexer.wk",
             "model.layers.13.self_attn.indexer.wq_b",
@@ -165,9 +155,6 @@
             "model.layers.13.self_attn.q_a_proj",
             "model.layers.13.self_attn.q_b_proj",
             "model.layers.14.mlp.gate",
-            "model.layers.14.mlp.shared_experts.down_proj",
-            "model.layers.14.mlp.shared_experts.gate_proj",
-            "model.layers.14.mlp.shared_experts.up_proj",
             "model.layers.14.self_attn.indexer.weights_proj",
             "model.layers.14.self_attn.indexer.wk",
             "model.layers.14.self_attn.indexer.wq_b",
@@ -177,9 +164,6 @@
             "model.layers.14.self_attn.q_a_proj",
             "model.layers.14.self_attn.q_b_proj",
             "model.layers.15.mlp.gate",
-            "model.layers.15.mlp.shared_experts.down_proj",
-            "model.layers.15.mlp.shared_experts.gate_proj",
-            "model.layers.15.mlp.shared_experts.up_proj",
             "model.layers.15.self_attn.indexer.weights_proj",
             "model.layers.15.self_attn.indexer.wk",
             "model.layers.15.self_attn.indexer.wq_b",
@@ -189,9 +173,6 @@
             "model.layers.15.self_attn.q_a_proj",
             "model.layers.15.self_attn.q_b_proj",
             "model.layers.16.mlp.gate",
-            "model.layers.16.mlp.shared_experts.down_proj",
-            "model.layers.16.mlp.shared_experts.gate_proj",
-            "model.layers.16.mlp.shared_experts.up_proj",
             "model.layers.16.self_attn.indexer.weights_proj",
             "model.layers.16.self_attn.indexer.wk",
             "model.layers.16.self_attn.indexer.wq_b",
@@ -201,9 +182,6 @@
             "model.layers.16.self_attn.q_a_proj",
             "model.layers.16.self_attn.q_b_proj",
             "model.layers.17.mlp.gate",
-            "model.layers.17.mlp.shared_experts.down_proj",
-            "model.layers.17.mlp.shared_experts.gate_proj",
-            "model.layers.17.mlp.shared_experts.up_proj",
             "model.layers.17.self_attn.indexer.weights_proj",
             "model.layers.17.self_attn.indexer.wk",
             "model.layers.17.self_attn.indexer.wq_b",
@@ -213,9 +191,6 @@
             "model.layers.17.self_attn.q_a_proj",
             "model.layers.17.self_attn.q_b_proj",
             "model.layers.18.mlp.gate",
-            "model.layers.18.mlp.shared_experts.down_proj",
-            "model.layers.18.mlp.shared_experts.gate_proj",
-            "model.layers.18.mlp.shared_experts.up_proj",
             "model.layers.18.self_attn.indexer.weights_proj",
             "model.layers.18.self_attn.indexer.wk",
             "model.layers.18.self_attn.indexer.wq_b",
@@ -225,9 +200,6 @@
             "model.layers.18.self_attn.q_a_proj",
             "model.layers.18.self_attn.q_b_proj",
             "model.layers.19.mlp.gate",
-            "model.layers.19.mlp.shared_experts.down_proj",
-            "model.layers.19.mlp.shared_experts.gate_proj",
-            "model.layers.19.mlp.shared_experts.up_proj",
             "model.layers.19.self_attn.indexer.weights_proj",
             "model.layers.19.self_attn.indexer.wk",
             "model.layers.19.self_attn.indexer.wq_b",
@@ -248,9 +220,6 @@
             "model.layers.2.self_attn.q_a_proj",
             "model.layers.2.self_attn.q_b_proj",
             "model.layers.20.mlp.gate",
-            "model.layers.20.mlp.shared_experts.down_proj",
-            "model.layers.20.mlp.shared_experts.gate_proj",
-            "model.layers.20.mlp.shared_experts.up_proj",
             "model.layers.20.self_attn.indexer.weights_proj",
             "model.layers.20.self_attn.indexer.wk",
             "model.layers.20.self_attn.indexer.wq_b",
@@ -260,9 +229,6 @@
             "model.layers.20.self_attn.q_a_proj",
             "model.layers.20.self_attn.q_b_proj",
             "model.layers.21.mlp.gate",
-            "model.layers.21.mlp.shared_experts.down_proj",
-            "model.layers.21.mlp.shared_experts.gate_proj",
-            "model.layers.21.mlp.shared_experts.up_proj",
             "model.layers.21.self_attn.indexer.weights_proj",
             "model.layers.21.self_attn.indexer.wk",
             "model.layers.21.self_attn.indexer.wq_b",
@@ -272,9 +238,6 @@
             "model.layers.21.self_attn.q_a_proj",
             "model.layers.21.self_attn.q_b_proj",
             "model.layers.22.mlp.gate",
-            "model.layers.22.mlp.shared_experts.down_proj",
-            "model.layers.22.mlp.shared_experts.gate_proj",
-            "model.layers.22.mlp.shared_experts.up_proj",
             "model.layers.22.self_attn.indexer.weights_proj",
             "model.layers.22.self_attn.indexer.wk",
             "model.layers.22.self_attn.indexer.wq_b",
@@ -284,9 +247,6 @@
             "model.layers.22.self_attn.q_a_proj",
             "model.layers.22.self_attn.q_b_proj",
             "model.layers.23.mlp.gate",
-            "model.layers.23.mlp.shared_experts.down_proj",
-            "model.layers.23.mlp.shared_experts.gate_proj",
-            "model.layers.23.mlp.shared_experts.up_proj",
             "model.layers.23.self_attn.indexer.weights_proj",
             "model.layers.23.self_attn.indexer.wk",
             "model.layers.23.self_attn.indexer.wq_b",
@@ -296,9 +256,6 @@
             "model.layers.23.self_attn.q_a_proj",
             "model.layers.23.self_attn.q_b_proj",
             "model.layers.24.mlp.gate",
-            "model.layers.24.mlp.shared_experts.down_proj",
-            "model.layers.24.mlp.shared_experts.gate_proj",
-            "model.layers.24.mlp.shared_experts.up_proj",
             "model.layers.24.self_attn.indexer.weights_proj",
             "model.layers.24.self_attn.indexer.wk",
             "model.layers.24.self_attn.indexer.wq_b",
@@ -308,9 +265,6 @@
             "model.layers.24.self_attn.q_a_proj",
             "model.layers.24.self_attn.q_b_proj",
             "model.layers.25.mlp.gate",
-            "model.layers.25.mlp.shared_experts.down_proj",
-            "model.layers.25.mlp.shared_experts.gate_proj",
-            "model.layers.25.mlp.shared_experts.up_proj",
             "model.layers.25.self_attn.indexer.weights_proj",
             "model.layers.25.self_attn.indexer.wk",
             "model.layers.25.self_attn.indexer.wq_b",
@@ -320,9 +274,6 @@
             "model.layers.25.self_attn.q_a_proj",
             "model.layers.25.self_attn.q_b_proj",
             "model.layers.26.mlp.gate",
-            "model.layers.26.mlp.shared_experts.down_proj",
-            "model.layers.26.mlp.shared_experts.gate_proj",
-            "model.layers.26.mlp.shared_experts.up_proj",
             "model.layers.26.self_attn.indexer.weights_proj",
             "model.layers.26.self_attn.indexer.wk",
             "model.layers.26.self_attn.indexer.wq_b",
@@ -332,9 +283,6 @@
             "model.layers.26.self_attn.q_a_proj",
             "model.layers.26.self_attn.q_b_proj",
             "model.layers.27.mlp.gate",
-            "model.layers.27.mlp.shared_experts.down_proj",
-            "model.layers.27.mlp.shared_experts.gate_proj",
-            "model.layers.27.mlp.shared_experts.up_proj",
             "model.layers.27.self_attn.indexer.weights_proj",
             "model.layers.27.self_attn.indexer.wk",
             "model.layers.27.self_attn.indexer.wq_b",
@@ -344,9 +292,6 @@
             "model.layers.27.self_attn.q_a_proj",
             "model.layers.27.self_attn.q_b_proj",
             "model.layers.28.mlp.gate",
-            "model.layers.28.mlp.shared_experts.down_proj",
-            "model.layers.28.mlp.shared_experts.gate_proj",
-            "model.layers.28.mlp.shared_experts.up_proj",
             "model.layers.28.self_attn.indexer.weights_proj",
             "model.layers.28.self_attn.indexer.wk",
             "model.layers.28.self_attn.indexer.wq_b",
@@ -356,9 +301,6 @@
             "model.layers.28.self_attn.q_a_proj",
             "model.layers.28.self_attn.q_b_proj",
             "model.layers.29.mlp.gate",
-            "model.layers.29.mlp.shared_experts.down_proj",
-            "model.layers.29.mlp.shared_experts.gate_proj",
-            "model.layers.29.mlp.shared_experts.up_proj",
             "model.layers.29.self_attn.indexer.weights_proj",
             "model.layers.29.self_attn.indexer.wk",
             "model.layers.29.self_attn.indexer.wq_b",
@@ -368,9 +310,6 @@
             "model.layers.29.self_attn.q_a_proj",
             "model.layers.29.self_attn.q_b_proj",
             "model.layers.3.mlp.gate",
-            "model.layers.3.mlp.shared_experts.down_proj",
-            "model.layers.3.mlp.shared_experts.gate_proj",
-            "model.layers.3.mlp.shared_experts.up_proj",
             "model.layers.3.self_attn.indexer.weights_proj",
             "model.layers.3.self_attn.indexer.wk",
             "model.layers.3.self_attn.indexer.wq_b",
@@ -380,9 +319,6 @@
             "model.layers.3.self_attn.q_a_proj",
             "model.layers.3.self_attn.q_b_proj",
             "model.layers.30.mlp.gate",
-            "model.layers.30.mlp.shared_experts.down_proj",
-            "model.layers.30.mlp.shared_experts.gate_proj",
-            "model.layers.30.mlp.shared_experts.up_proj",
             "model.layers.30.self_attn.indexer.weights_proj",
             "model.layers.30.self_attn.indexer.wk",
             "model.layers.30.self_attn.indexer.wq_b",
@@ -392,9 +328,6 @@
             "model.layers.30.self_attn.q_a_proj",
             "model.layers.30.self_attn.q_b_proj",
             "model.layers.31.mlp.gate",
-            "model.layers.31.mlp.shared_experts.down_proj",
-            "model.layers.31.mlp.shared_experts.gate_proj",
-            "model.layers.31.mlp.shared_experts.up_proj",
             "model.layers.31.self_attn.indexer.weights_proj",
             "model.layers.31.self_attn.indexer.wk",
             "model.layers.31.self_attn.indexer.wq_b",
@@ -404,9 +337,6 @@
             "model.layers.31.self_attn.q_a_proj",
             "model.layers.31.self_attn.q_b_proj",
             "model.layers.32.mlp.gate",
-            "model.layers.32.mlp.shared_experts.down_proj",
-            "model.layers.32.mlp.shared_experts.gate_proj",
-            "model.layers.32.mlp.shared_experts.up_proj",
             "model.layers.32.self_attn.indexer.weights_proj",
             "model.layers.32.self_attn.indexer.wk",
             "model.layers.32.self_attn.indexer.wq_b",
@@ -416,9 +346,6 @@
             "model.layers.32.self_attn.q_a_proj",
             "model.layers.32.self_attn.q_b_proj",
             "model.layers.33.mlp.gate",
-            "model.layers.33.mlp.shared_experts.down_proj",
-            "model.layers.33.mlp.shared_experts.gate_proj",
-            "model.layers.33.mlp.shared_experts.up_proj",
             "model.layers.33.self_attn.indexer.weights_proj",
             "model.layers.33.self_attn.indexer.wk",
             "model.layers.33.self_attn.indexer.wq_b",
@@ -428,9 +355,6 @@
             "model.layers.33.self_attn.q_a_proj",
             "model.layers.33.self_attn.q_b_proj",
             "model.layers.34.mlp.gate",
-            "model.layers.34.mlp.shared_experts.down_proj",
-            "model.layers.34.mlp.shared_experts.gate_proj",
-            "model.layers.34.mlp.shared_experts.up_proj",
             "model.layers.34.self_attn.indexer.weights_proj",
             "model.layers.34.self_attn.indexer.wk",
             "model.layers.34.self_attn.indexer.wq_b",
@@ -440,9 +364,6 @@
             "model.layers.34.self_attn.q_a_proj",
             "model.layers.34.self_attn.q_b_proj",
             "model.layers.35.mlp.gate",
-            "model.layers.35.mlp.shared_experts.down_proj",
-            "model.layers.35.mlp.shared_experts.gate_proj",
-            "model.layers.35.mlp.shared_experts.up_proj",
             "model.layers.35.self_attn.indexer.weights_proj",
             "model.layers.35.self_attn.indexer.wk",
             "model.layers.35.self_attn.indexer.wq_b",
@@ -452,9 +373,6 @@
             "model.layers.35.self_attn.q_a_proj",
             "model.layers.35.self_attn.q_b_proj",
             "model.layers.36.mlp.gate",
-            "model.layers.36.mlp.shared_experts.down_proj",
-            "model.layers.36.mlp.shared_experts.gate_proj",
-            "model.layers.36.mlp.shared_experts.up_proj",
             "model.layers.36.self_attn.indexer.weights_proj",
             "model.layers.36.self_attn.indexer.wk",
             "model.layers.36.self_attn.indexer.wq_b",
@@ -464,9 +382,6 @@
             "model.layers.36.self_attn.q_a_proj",
             "model.layers.36.self_attn.q_b_proj",
             "model.layers.37.mlp.gate",
-            "model.layers.37.mlp.shared_experts.down_proj",
-            "model.layers.37.mlp.shared_experts.gate_proj",
-            "model.layers.37.mlp.shared_experts.up_proj",
             "model.layers.37.self_attn.indexer.weights_proj",
             "model.layers.37.self_attn.indexer.wk",
             "model.layers.37.self_attn.indexer.wq_b",
@@ -476,9 +391,6 @@
             "model.layers.37.self_attn.q_a_proj",
             "model.layers.37.self_attn.q_b_proj",
             "model.layers.38.mlp.gate",
-            "model.layers.38.mlp.shared_experts.down_proj",
-            "model.layers.38.mlp.shared_experts.gate_proj",
-            "model.layers.38.mlp.shared_experts.up_proj",
             "model.layers.38.self_attn.indexer.weights_proj",
             "model.layers.38.self_attn.indexer.wk",
             "model.layers.38.self_attn.indexer.wq_b",
@@ -488,9 +400,6 @@
             "model.layers.38.self_attn.q_a_proj",
             "model.layers.38.self_attn.q_b_proj",
             "model.layers.39.mlp.gate",
-            "model.layers.39.mlp.shared_experts.down_proj",
-            "model.layers.39.mlp.shared_experts.gate_proj",
-            "model.layers.39.mlp.shared_experts.up_proj",
             "model.layers.39.self_attn.indexer.weights_proj",
             "model.layers.39.self_attn.indexer.wk",
             "model.layers.39.self_attn.indexer.wq_b",
@@ -500,9 +409,6 @@
             "model.layers.39.self_attn.q_a_proj",
             "model.layers.39.self_attn.q_b_proj",
             "model.layers.4.mlp.gate",
-            "model.layers.4.mlp.shared_experts.down_proj",
-            "model.layers.4.mlp.shared_experts.gate_proj",
-            "model.layers.4.mlp.shared_experts.up_proj",
             "model.layers.4.self_attn.indexer.weights_proj",
             "model.layers.4.self_attn.indexer.wk",
             "model.layers.4.self_attn.indexer.wq_b",
@@ -512,9 +418,6 @@
             "model.layers.4.self_attn.q_a_proj",
             "model.layers.4.self_attn.q_b_proj",
             "model.layers.40.mlp.gate",
-            "model.layers.40.mlp.shared_experts.down_proj",
-            "model.layers.40.mlp.shared_experts.gate_proj",
-            "model.layers.40.mlp.shared_experts.up_proj",
             "model.layers.40.self_attn.indexer.weights_proj",
             "model.layers.40.self_attn.indexer.wk",
             "model.layers.40.self_attn.indexer.wq_b",
@@ -524,9 +427,6 @@
             "model.layers.40.self_attn.q_a_proj",
             "model.layers.40.self_attn.q_b_proj",
             "model.layers.41.mlp.gate",
-            "model.layers.41.mlp.shared_experts.down_proj",
-            "model.layers.41.mlp.shared_experts.gate_proj",
-            "model.layers.41.mlp.shared_experts.up_proj",
             "model.layers.41.self_attn.indexer.weights_proj",
             "model.layers.41.self_attn.indexer.wk",
             "model.layers.41.self_attn.indexer.wq_b",
@@ -536,9 +436,6 @@
             "model.layers.41.self_attn.q_a_proj",
             "model.layers.41.self_attn.q_b_proj",
             "model.layers.42.mlp.gate",
-            "model.layers.42.mlp.shared_experts.down_proj",
-            "model.layers.42.mlp.shared_experts.gate_proj",
-            "model.layers.42.mlp.shared_experts.up_proj",
             "model.layers.42.self_attn.indexer.weights_proj",
             "model.layers.42.self_attn.indexer.wk",
             "model.layers.42.self_attn.indexer.wq_b",
@@ -548,9 +445,6 @@
             "model.layers.42.self_attn.q_a_proj",
             "model.layers.42.self_attn.q_b_proj",
             "model.layers.43.mlp.gate",
-            "model.layers.43.mlp.shared_experts.down_proj",
-            "model.layers.43.mlp.shared_experts.gate_proj",
-            "model.layers.43.mlp.shared_experts.up_proj",
             "model.layers.43.self_attn.indexer.weights_proj",
             "model.layers.43.self_attn.indexer.wk",
             "model.layers.43.self_attn.indexer.wq_b",
@@ -560,9 +454,6 @@
             "model.layers.43.self_attn.q_a_proj",
             "model.layers.43.self_attn.q_b_proj",
             "model.layers.44.mlp.gate",
-            "model.layers.44.mlp.shared_experts.down_proj",
-            "model.layers.44.mlp.shared_experts.gate_proj",
-            "model.layers.44.mlp.shared_experts.up_proj",
             "model.layers.44.self_attn.indexer.weights_proj",
             "model.layers.44.self_attn.indexer.wk",
             "model.layers.44.self_attn.indexer.wq_b",
@@ -572,9 +463,6 @@
             "model.layers.44.self_attn.q_a_proj",
             "model.layers.44.self_attn.q_b_proj",
             "model.layers.45.mlp.gate",
-            "model.layers.45.mlp.shared_experts.down_proj",
-            "model.layers.45.mlp.shared_experts.gate_proj",
-            "model.layers.45.mlp.shared_experts.up_proj",
             "model.layers.45.self_attn.indexer.weights_proj",
             "model.layers.45.self_attn.indexer.wk",
             "model.layers.45.self_attn.indexer.wq_b",
@@ -584,9 +472,6 @@
             "model.layers.45.self_attn.q_a_proj",
             "model.layers.45.self_attn.q_b_proj",
             "model.layers.46.mlp.gate",
-            "model.layers.46.mlp.shared_experts.down_proj",
-            "model.layers.46.mlp.shared_experts.gate_proj",
-            "model.layers.46.mlp.shared_experts.up_proj",
             "model.layers.46.self_attn.indexer.weights_proj",
             "model.layers.46.self_attn.indexer.wk",
             "model.layers.46.self_attn.indexer.wq_b",
@@ -596,9 +481,6 @@
             "model.layers.46.self_attn.q_a_proj",
             "model.layers.46.self_attn.q_b_proj",
             "model.layers.47.mlp.gate",
-            "model.layers.47.mlp.shared_experts.down_proj",
-            "model.layers.47.mlp.shared_experts.gate_proj",
-            "model.layers.47.mlp.shared_experts.up_proj",
             "model.layers.47.self_attn.indexer.weights_proj",
             "model.layers.47.self_attn.indexer.wk",
             "model.layers.47.self_attn.indexer.wq_b",
@@ -608,9 +490,6 @@
             "model.layers.47.self_attn.q_a_proj",
             "model.layers.47.self_attn.q_b_proj",
             "model.layers.48.mlp.gate",
-            "model.layers.48.mlp.shared_experts.down_proj",
-            "model.layers.48.mlp.shared_experts.gate_proj",
-            "model.layers.48.mlp.shared_experts.up_proj",
             "model.layers.48.self_attn.indexer.weights_proj",
             "model.layers.48.self_attn.indexer.wk",
             "model.layers.48.self_attn.indexer.wq_b",
@@ -620,9 +499,6 @@
             "model.layers.48.self_attn.q_a_proj",
             "model.layers.48.self_attn.q_b_proj",
             "model.layers.49.mlp.gate",
-            "model.layers.49.mlp.shared_experts.down_proj",
-            "model.layers.49.mlp.shared_experts.gate_proj",
-            "model.layers.49.mlp.shared_experts.up_proj",
             "model.layers.49.self_attn.indexer.weights_proj",
             "model.layers.49.self_attn.indexer.wk",
             "model.layers.49.self_attn.indexer.wq_b",
@@ -632,9 +508,6 @@
             "model.layers.49.self_attn.q_a_proj",
             "model.layers.49.self_attn.q_b_proj",
             "model.layers.5.mlp.gate",
-            "model.layers.5.mlp.shared_experts.down_proj",
-            "model.layers.5.mlp.shared_experts.gate_proj",
-            "model.layers.5.mlp.shared_experts.up_proj",
             "model.layers.5.self_attn.indexer.weights_proj",
             "model.layers.5.self_attn.indexer.wk",
             "model.layers.5.self_attn.indexer.wq_b",
@@ -644,9 +517,6 @@
             "model.layers.5.self_attn.q_a_proj",
             "model.layers.5.self_attn.q_b_proj",
             "model.layers.50.mlp.gate",
-            "model.layers.50.mlp.shared_experts.down_proj",
-            "model.layers.50.mlp.shared_experts.gate_proj",
-            "model.layers.50.mlp.shared_experts.up_proj",
             "model.layers.50.self_attn.indexer.weights_proj",
             "model.layers.50.self_attn.indexer.wk",
             "model.layers.50.self_attn.indexer.wq_b",
@@ -656,9 +526,6 @@
             "model.layers.50.self_attn.q_a_proj",
             "model.layers.50.self_attn.q_b_proj",
             "model.layers.51.mlp.gate",
-            "model.layers.51.mlp.shared_experts.down_proj",
-            "model.layers.51.mlp.shared_experts.gate_proj",
-            "model.layers.51.mlp.shared_experts.up_proj",
             "model.layers.51.self_attn.indexer.weights_proj",
             "model.layers.51.self_attn.indexer.wk",
             "model.layers.51.self_attn.indexer.wq_b",
@@ -668,9 +535,6 @@
             "model.layers.51.self_attn.q_a_proj",
             "model.layers.51.self_attn.q_b_proj",
             "model.layers.52.mlp.gate",
-            "model.layers.52.mlp.shared_experts.down_proj",
-            "model.layers.52.mlp.shared_experts.gate_proj",
-            "model.layers.52.mlp.shared_experts.up_proj",
             "model.layers.52.self_attn.indexer.weights_proj",
             "model.layers.52.self_attn.indexer.wk",
             "model.layers.52.self_attn.indexer.wq_b",
@@ -680,9 +544,6 @@
             "model.layers.52.self_attn.q_a_proj",
             "model.layers.52.self_attn.q_b_proj",
             "model.layers.53.mlp.gate",
-            "model.layers.53.mlp.shared_experts.down_proj",
-            "model.layers.53.mlp.shared_experts.gate_proj",
-            "model.layers.53.mlp.shared_experts.up_proj",
             "model.layers.53.self_attn.indexer.weights_proj",
             "model.layers.53.self_attn.indexer.wk",
             "model.layers.53.self_attn.indexer.wq_b",
@@ -692,9 +553,6 @@
             "model.layers.53.self_attn.q_a_proj",
             "model.layers.53.self_attn.q_b_proj",
             "model.layers.54.mlp.gate",
-            "model.layers.54.mlp.shared_experts.down_proj",
-            "model.layers.54.mlp.shared_experts.gate_proj",
-            "model.layers.54.mlp.shared_experts.up_proj",
             "model.layers.54.self_attn.indexer.weights_proj",
             "model.layers.54.self_attn.indexer.wk",
             "model.layers.54.self_attn.indexer.wq_b",
@@ -704,9 +562,6 @@
             "model.layers.54.self_attn.q_a_proj",
             "model.layers.54.self_attn.q_b_proj",
             "model.layers.55.mlp.gate",
-            "model.layers.55.mlp.shared_experts.down_proj",
-            "model.layers.55.mlp.shared_experts.gate_proj",
-            "model.layers.55.mlp.shared_experts.up_proj",
             "model.layers.55.self_attn.indexer.weights_proj",
             "model.layers.55.self_attn.indexer.wk",
             "model.layers.55.self_attn.indexer.wq_b",
@@ -716,9 +571,6 @@
             "model.layers.55.self_attn.q_a_proj",
             "model.layers.55.self_attn.q_b_proj",
             "model.layers.56.mlp.gate",
-            "model.layers.56.mlp.shared_experts.down_proj",
-            "model.layers.56.mlp.shared_experts.gate_proj",
-            "model.layers.56.mlp.shared_experts.up_proj",
             "model.layers.56.self_attn.indexer.weights_proj",
             "model.layers.56.self_attn.indexer.wk",
             "model.layers.56.self_attn.indexer.wq_b",
@@ -728,9 +580,6 @@
             "model.layers.56.self_attn.q_a_proj",
             "model.layers.56.self_attn.q_b_proj",
             "model.layers.57.mlp.gate",
-            "model.layers.57.mlp.shared_experts.down_proj",
-            "model.layers.57.mlp.shared_experts.gate_proj",
-            "model.layers.57.mlp.shared_experts.up_proj",
             "model.layers.57.self_attn.indexer.weights_proj",
             "model.layers.57.self_attn.indexer.wk",
             "model.layers.57.self_attn.indexer.wq_b",
@@ -740,9 +589,6 @@
             "model.layers.57.self_attn.q_a_proj",
             "model.layers.57.self_attn.q_b_proj",
             "model.layers.58.mlp.gate",
-            "model.layers.58.mlp.shared_experts.down_proj",
-            "model.layers.58.mlp.shared_experts.gate_proj",
-            "model.layers.58.mlp.shared_experts.up_proj",
             "model.layers.58.self_attn.indexer.weights_proj",
             "model.layers.58.self_attn.indexer.wk",
             "model.layers.58.self_attn.indexer.wq_b",
@@ -752,9 +598,6 @@
             "model.layers.58.self_attn.q_a_proj",
             "model.layers.58.self_attn.q_b_proj",
             "model.layers.59.mlp.gate",
-            "model.layers.59.mlp.shared_experts.down_proj",
-            "model.layers.59.mlp.shared_experts.gate_proj",
-            "model.layers.59.mlp.shared_experts.up_proj",
             "model.layers.59.self_attn.indexer.weights_proj",
             "model.layers.59.self_attn.indexer.wk",
             "model.layers.59.self_attn.indexer.wq_b",
@@ -764,9 +607,6 @@
             "model.layers.59.self_attn.q_a_proj",
             "model.layers.59.self_attn.q_b_proj",
             "model.layers.6.mlp.gate",
-            "model.layers.6.mlp.shared_experts.down_proj",
-            "model.layers.6.mlp.shared_experts.gate_proj",
-            "model.layers.6.mlp.shared_experts.up_proj",
             "model.layers.6.self_attn.indexer.weights_proj",
             "model.layers.6.self_attn.indexer.wk",
             "model.layers.6.self_attn.indexer.wq_b",
@@ -776,9 +616,6 @@
             "model.layers.6.self_attn.q_a_proj",
             "model.layers.6.self_attn.q_b_proj",
             "model.layers.60.mlp.gate",
-            "model.layers.60.mlp.shared_experts.down_proj",
-            "model.layers.60.mlp.shared_experts.gate_proj",
-            "model.layers.60.mlp.shared_experts.up_proj",
             "model.layers.60.self_attn.indexer.weights_proj",
             "model.layers.60.self_attn.indexer.wk",
             "model.layers.60.self_attn.indexer.wq_b",
@@ -788,9 +625,6 @@
             "model.layers.60.self_attn.q_a_proj",
             "model.layers.60.self_attn.q_b_proj",
             "model.layers.61.mlp.gate",
-            "model.layers.61.mlp.shared_experts.down_proj",
-            "model.layers.61.mlp.shared_experts.gate_proj",
-            "model.layers.61.mlp.shared_experts.up_proj",
             "model.layers.61.self_attn.indexer.weights_proj",
             "model.layers.61.self_attn.indexer.wk",
             "model.layers.61.self_attn.indexer.wq_b",
@@ -800,9 +634,6 @@
             "model.layers.61.self_attn.q_a_proj",
             "model.layers.61.self_attn.q_b_proj",
             "model.layers.62.mlp.gate",
-            "model.layers.62.mlp.shared_experts.down_proj",
-            "model.layers.62.mlp.shared_experts.gate_proj",
-            "model.layers.62.mlp.shared_experts.up_proj",
             "model.layers.62.self_attn.indexer.weights_proj",
             "model.layers.62.self_attn.indexer.wk",
             "model.layers.62.self_attn.indexer.wq_b",
@@ -812,9 +643,6 @@
             "model.layers.62.self_attn.q_a_proj",
             "model.layers.62.self_attn.q_b_proj",
             "model.layers.63.mlp.gate",
-            "model.layers.63.mlp.shared_experts.down_proj",
-            "model.layers.63.mlp.shared_experts.gate_proj",
-            "model.layers.63.mlp.shared_experts.up_proj",
             "model.layers.63.self_attn.indexer.weights_proj",
             "model.layers.63.self_attn.indexer.wk",
             "model.layers.63.self_attn.indexer.wq_b",
@@ -824,9 +652,6 @@
             "model.layers.63.self_attn.q_a_proj",
             "model.layers.63.self_attn.q_b_proj",
             "model.layers.64.mlp.gate",
-            "model.layers.64.mlp.shared_experts.down_proj",
-            "model.layers.64.mlp.shared_experts.gate_proj",
-            "model.layers.64.mlp.shared_experts.up_proj",
             "model.layers.64.self_attn.indexer.weights_proj",
             "model.layers.64.self_attn.indexer.wk",
             "model.layers.64.self_attn.indexer.wq_b",
@@ -836,9 +661,6 @@
             "model.layers.64.self_attn.q_a_proj",
             "model.layers.64.self_attn.q_b_proj",
             "model.layers.65.mlp.gate",
-            "model.layers.65.mlp.shared_experts.down_proj",
-            "model.layers.65.mlp.shared_experts.gate_proj",
-            "model.layers.65.mlp.shared_experts.up_proj",
             "model.layers.65.self_attn.indexer.weights_proj",
             "model.layers.65.self_attn.indexer.wk",
             "model.layers.65.self_attn.indexer.wq_b",
@@ -848,9 +670,6 @@
             "model.layers.65.self_attn.q_a_proj",
             "model.layers.65.self_attn.q_b_proj",
             "model.layers.66.mlp.gate",
-            "model.layers.66.mlp.shared_experts.down_proj",
-            "model.layers.66.mlp.shared_experts.gate_proj",
-            "model.layers.66.mlp.shared_experts.up_proj",
             "model.layers.66.self_attn.indexer.weights_proj",
             "model.layers.66.self_attn.indexer.wk",
             "model.layers.66.self_attn.indexer.wq_b",
@@ -860,9 +679,6 @@
             "model.layers.66.self_attn.q_a_proj",
             "model.layers.66.self_attn.q_b_proj",
             "model.layers.67.mlp.gate",
-            "model.layers.67.mlp.shared_experts.down_proj",
-            "model.layers.67.mlp.shared_experts.gate_proj",
-            "model.layers.67.mlp.shared_experts.up_proj",
             "model.layers.67.self_attn.indexer.weights_proj",
             "model.layers.67.self_attn.indexer.wk",
             "model.layers.67.self_attn.indexer.wq_b",
@@ -872,9 +688,6 @@
             "model.layers.67.self_attn.q_a_proj",
             "model.layers.67.self_attn.q_b_proj",
             "model.layers.68.mlp.gate",
-            "model.layers.68.mlp.shared_experts.down_proj",
-            "model.layers.68.mlp.shared_experts.gate_proj",
-            "model.layers.68.mlp.shared_experts.up_proj",
             "model.layers.68.self_attn.indexer.weights_proj",
             "model.layers.68.self_attn.indexer.wk",
             "model.layers.68.self_attn.indexer.wq_b",
@@ -884,9 +697,6 @@
             "model.layers.68.self_attn.q_a_proj",
             "model.layers.68.self_attn.q_b_proj",
             "model.layers.69.mlp.gate",
-            "model.layers.69.mlp.shared_experts.down_proj",
-            "model.layers.69.mlp.shared_experts.gate_proj",
-            "model.layers.69.mlp.shared_experts.up_proj",
             "model.layers.69.self_attn.indexer.weights_proj",
             "model.layers.69.self_attn.indexer.wk",
             "model.layers.69.self_attn.indexer.wq_b",
@@ -896,9 +706,6 @@
             "model.layers.69.self_attn.q_a_proj",
             "model.layers.69.self_attn.q_b_proj",
             "model.layers.7.mlp.gate",
-            "model.layers.7.mlp.shared_experts.down_proj",
-            "model.layers.7.mlp.shared_experts.gate_proj",
-            "model.layers.7.mlp.shared_experts.up_proj",
             "model.layers.7.self_attn.indexer.weights_proj",
             "model.layers.7.self_attn.indexer.wk",
             "model.layers.7.self_attn.indexer.wq_b",
@@ -908,9 +715,6 @@
             "model.layers.7.self_attn.q_a_proj",
             "model.layers.7.self_attn.q_b_proj",
             "model.layers.70.mlp.gate",
-            "model.layers.70.mlp.shared_experts.down_proj",
-            "model.layers.70.mlp.shared_experts.gate_proj",
-            "model.layers.70.mlp.shared_experts.up_proj",
             "model.layers.70.self_attn.indexer.weights_proj",
             "model.layers.70.self_attn.indexer.wk",
             "model.layers.70.self_attn.indexer.wq_b",
@@ -920,9 +724,6 @@
             "model.layers.70.self_attn.q_a_proj",
             "model.layers.70.self_attn.q_b_proj",
             "model.layers.71.mlp.gate",
-            "model.layers.71.mlp.shared_experts.down_proj",
-            "model.layers.71.mlp.shared_experts.gate_proj",
-            "model.layers.71.mlp.shared_experts.up_proj",
             "model.layers.71.self_attn.indexer.weights_proj",
             "model.layers.71.self_attn.indexer.wk",
             "model.layers.71.self_attn.indexer.wq_b",
@@ -932,9 +733,6 @@
             "model.layers.71.self_attn.q_a_proj",
             "model.layers.71.self_attn.q_b_proj",
             "model.layers.72.mlp.gate",
-            "model.layers.72.mlp.shared_experts.down_proj",
-            "model.layers.72.mlp.shared_experts.gate_proj",
-            "model.layers.72.mlp.shared_experts.up_proj",
             "model.layers.72.self_attn.indexer.weights_proj",
             "model.layers.72.self_attn.indexer.wk",
             "model.layers.72.self_attn.indexer.wq_b",
@@ -944,9 +742,6 @@
             "model.layers.72.self_attn.q_a_proj",
             "model.layers.72.self_attn.q_b_proj",
             "model.layers.73.mlp.gate",
-            "model.layers.73.mlp.shared_experts.down_proj",
-            "model.layers.73.mlp.shared_experts.gate_proj",
-            "model.layers.73.mlp.shared_experts.up_proj",
             "model.layers.73.self_attn.indexer.weights_proj",
             "model.layers.73.self_attn.indexer.wk",
             "model.layers.73.self_attn.indexer.wq_b",
@@ -956,9 +751,6 @@
             "model.layers.73.self_attn.q_a_proj",
             "model.layers.73.self_attn.q_b_proj",
             "model.layers.74.mlp.gate",
-            "model.layers.74.mlp.shared_experts.down_proj",
-            "model.layers.74.mlp.shared_experts.gate_proj",
-            "model.layers.74.mlp.shared_experts.up_proj",
             "model.layers.74.self_attn.indexer.weights_proj",
             "model.layers.74.self_attn.indexer.wk",
             "model.layers.74.self_attn.indexer.wq_b",
@@ -968,9 +760,6 @@
             "model.layers.74.self_attn.q_a_proj",
             "model.layers.74.self_attn.q_b_proj",
             "model.layers.75.mlp.gate",
-            "model.layers.75.mlp.shared_experts.down_proj",
-            "model.layers.75.mlp.shared_experts.gate_proj",
-            "model.layers.75.mlp.shared_experts.up_proj",
             "model.layers.75.self_attn.indexer.weights_proj",
             "model.layers.75.self_attn.indexer.wk",
             "model.layers.75.self_attn.indexer.wq_b",
@@ -980,9 +769,6 @@
             "model.layers.75.self_attn.q_a_proj",
             "model.layers.75.self_attn.q_b_proj",
             "model.layers.76.mlp.gate",
-            "model.layers.76.mlp.shared_experts.down_proj",
-            "model.layers.76.mlp.shared_experts.gate_proj",
-            "model.layers.76.mlp.shared_experts.up_proj",
             "model.layers.76.self_attn.indexer.weights_proj",
             "model.layers.76.self_attn.indexer.wk",
             "model.layers.76.self_attn.indexer.wq_b",
@@ -992,9 +778,6 @@
             "model.layers.76.self_attn.q_a_proj",
             "model.layers.76.self_attn.q_b_proj",
             "model.layers.77.mlp.gate",
-            "model.layers.77.mlp.shared_experts.down_proj",
-            "model.layers.77.mlp.shared_experts.gate_proj",
-            "model.layers.77.mlp.shared_experts.up_proj",
             "model.layers.77.self_attn.indexer.weights_proj",
             "model.layers.77.self_attn.indexer.wk",
             "model.layers.77.self_attn.indexer.wq_b",
@@ -1004,9 +787,6 @@
             "model.layers.77.self_attn.q_a_proj",
             "model.layers.77.self_attn.q_b_proj",
             "model.layers.78.mlp.gate",
-            "model.layers.78.mlp.shared_experts.down_proj",
-            "model.layers.78.mlp.shared_experts.gate_proj",
-            "model.layers.78.mlp.shared_experts.up_proj",
             "model.layers.78.self_attn.indexer.weights_proj",
             "model.layers.78.self_attn.indexer.wk",
             "model.layers.78.self_attn.indexer.wq_b",
@@ -1016,9 +796,6 @@
             "model.layers.78.self_attn.q_a_proj",
             "model.layers.78.self_attn.q_b_proj",
             "model.layers.8.mlp.gate",
-            "model.layers.8.mlp.shared_experts.down_proj",
-            "model.layers.8.mlp.shared_experts.gate_proj",
-            "model.layers.8.mlp.shared_experts.up_proj",
             "model.layers.8.self_attn.indexer.weights_proj",
             "model.layers.8.self_attn.indexer.wk",
             "model.layers.8.self_attn.indexer.wq_b",
@@ -1028,9 +805,6 @@
             "model.layers.8.self_attn.q_a_proj",
             "model.layers.8.self_attn.q_b_proj",
             "model.layers.9.mlp.gate",
-            "model.layers.9.mlp.shared_experts.down_proj",
-            "model.layers.9.mlp.shared_experts.gate_proj",
-            "model.layers.9.mlp.shared_experts.up_proj",
             "model.layers.9.self_attn.indexer.weights_proj",
             "model.layers.9.self_attn.indexer.wk",
             "model.layers.9.self_attn.indexer.wq_b",
@@ -1048,7 +822,7 @@
         "kv_cache_quant_config": {},
         "kv_cache_post_rope": false,
         "quant_mode": "eager_mode",
-        "version": "0.12+6ff6457c80",
+        "version": "0.12+4f9d2296257",
         "export": {
             "kv_cache_group": [],
             "min_kv_scale": 0.0,

model-00005-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8c329a5a9c83a678da7f9e02fed250f1372a9baefffaad01120adfda551b4b
-size 1737703968
+oid sha256:a26940b6f9473db94179144a15fe63cbfec50ecf5810476713e0cb8080dffb94
+size 1682260856

model-00009-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a168b828b2aa13eff829b9fc91b62d84ba55c2262e941b3e0e6c09bb10f8be0c
-size 1737704104
+oid sha256:8d56e5119dca52c43d9ce31a1f1064923ef2e8202739acb5b1ff5b90a9e01f0e
+size 1682260992

model-00012-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e84e133b5f5178b1d545f3987354e3ccdef25893dfc3db374b9bed6c0f07564
-size 1463997064
+oid sha256:5002e1ff5310504dd2531d6e613c57277dda63c4c02caf04afb3113136defdcb
+size 1427034960

model-00013-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee04729368cd144dbee1d0293fc019262b68719fb14135ef0bfcf8699a9b96d8
-size 1697595184
+oid sha256:4ade48d852d60663273770aad7bc351a5b7fa850b1af6ba73fb4e273e2ac5efe
+size 1679114128

model-00016-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85929ef0c5fddc04dca3c4c970661beefcfc806c639175cd0879db37990a39d1
-size 1737703944
+oid sha256:a85f66294ada19805d5c6ec0727f15a4f3aa767ba0d635a749fefa6232dc136c
+size 1682260832

model-00020-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ac78d6c4f82520cdf579ecf6fa3de02bb6deae854f523f429927c7e175fea1
-size 1737704080
+oid sha256:5e6ade5c8835ddd304840e568a17b344c7673e834a345598ff8489207bac6d1a
+size 1682260968

model-00024-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcdf5e8827c7ff29073f347d6469bf81cc6c87d34a15f922cfc272ad0204768
-size 1737704208
+oid sha256:cf870134763fedf5defb298ec6d3342b7366c6ae3ceb4c7779f1044659d101d3
+size 1682261096

model-00027-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a2933fa278d54b927b17712a0288881d4cee84c8aeae6f51f6b0fe5b6b69f37
-size 1737703928
+oid sha256:e4127b76fdd507616a5f93b9d16131f162804098c66aba63bfc05ed005138518
+size 1682260816

model-00031-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f29561964396e1ca591a1364e3c8e5b367d4811535f9d1e8f34ef70509c8255e
-size 1737704056
+oid sha256:9bbf7e880aff7f656ac96a927ee8467554096615ab15fd29def1d9a524b8f17c
+size 1682260944

model-00035-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc5dfbc9eb03d2b03f01ad940181dcd2a8a20052608ce018dab286e2801d3ae
-size 1737704184
+oid sha256:c58f27a3677f3457973dcc1fc7d422dec1d1c4c612d150859d68e63435038a8c
+size 1682261072

model-00038-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1056460f7a62d1d87fe59bd78ca059636fb386daf3b2f3c2eef39e431f2f45f0
-size 2260038664
+oid sha256:907e3c6c2725a6abe9e83e5f0de7f09c56e3241fbcebcc141262333d7215b114
+size 2204595600

model-00042-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fadee28237027195440ca9060d61b775643cdf8069994423c174d029322fb4f
-size 1737703968
+oid sha256:b61be60b23afe1c1a755114260b96f54500b0f094eefdea454da6c67c5f8fe71
+size 1682260848

model-00046-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65c4c62366b02c04f356f71921833f4f39280475b618042d414f74786ed8e6e
-size 1737704104
+oid sha256:080ff780e2983db8bcc6a8865da8b8374df552dafd26233d67ca30206356437a
+size 1682260992

model-00049-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe94fbdeecb5ceee200704747e2a9b0f7a7178afc7eca27523d38273d47577e
-size 1445516008
+oid sha256:c0989339b49451487e78f19bbcbee17e995a4ffa04520d229e1218b400e81a9c
+size 1427034952

model-00050-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c25eedbdd6843c3ffc52f0ca9e5ede35353f5bab25f204b99f78dd499a2cc5f8
-size 1716076232
+oid sha256:867476ef4b292c18711b45871340d23ec9b9e285cc234ad1818ccd845392dc64
+size 1679114136

model-00053-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de232a272294b0bf711d7ba4899350fd345dd65860276db77bfdf8b4d5965627
-size 1737703944
+oid sha256:bca11cf1231578e0485be38ac5d7fc0544b646af627850d39403084bfd2d9921
+size 1682260824

model-00057-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abac992f5365d82587df1ba1125d5ee1d6f58696ea3bc6d4fb17a7080fe33a6
-size 1737704080
+oid sha256:8ff9428e85a99b88164af6403d8fab1e6c4a699651eb5ebd91c455b88e990a83
+size 1682260968

model-00061-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf64238281755cef465ce9fe48a7ef9146bd8b8fc251fd13cffec87f7a7add7b
-size 1737704216
+oid sha256:efa5126807b7bc25a590f9ee0c02516137657ce006a104d8f7b54dcbd1b17375
+size 1682261096

model-00064-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e040342a3c2ceaeca0eafdeb5fdf90576dab6dfd4526576b3383ef9f9e8a946
-size 1737703920
+oid sha256:867a8b3e8625da9dd1b1aeac6691ba540322de5a6e3b5a0936f40e5c4df7fc0f
+size 1682260808

model-00068-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ab3971c913dad9b661d9e34973ce3869c1954c32116dc8cb26672ae9119d1b
-size 1737704056
+oid sha256:ce867f0559fe9dd775277289ff3dc54b90b06dfb19f91a1f82462aba81a8e7ec
+size 1682260944

model-00072-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e2e4ec17c04e96054acf45df173eda96602bb3b4eaca6345a5b8d744a62845
-size 1737704192
+oid sha256:adea37d14131466cde43ec290f49b91ddd55d6d0d5e884ce7aed82020aebef57
+size 1682261080

model-00075-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a4e373b930792e2c8ed87f32226e303259420ad47cf142215668c6dd313a73
-size 1737703840
+oid sha256:36296ded6050f0883702ebf714ce3e071da038ebefc73ce4b1f9777a54fc0843
+size 1682260728

model-00079-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e826f51fc7c5225d4f611d624051418262c4171775140f03130326e271a5d67b
-size 1737703808
+oid sha256:49a9a85d5771f0d9531f6bc91a3e8e6d75d3c1d30c6d6b847ba082207d3a9cde
+size 1682260688

model-00083-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b74cbd487dc3f7c14df682cb9934e00f1c7b219a17e9260328554f8cbd4a856
-size 1737704168
+oid sha256:39d7827f3b63df872dc668d129da2216854a1f130e01018f1fc0d11033d5777e
+size 1682261048

model-00086-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7dea58401a8f715a6226a234024900544a1696158fd86a7ece4602b7b02b860
-size 1737703872
+oid sha256:3bb4af0115f0ffd8ef01b5328b0afde0dcc53c6b63433608596590954467dc08
+size 1682260752

model-00090-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4754b87dca269f473a43c78959d2394a76648740cfa6692a6c95711d07853e32
-size 1737704008
+oid sha256:47c0ca34a40a1af1d8dafdcf9306932b351b78b369546f32fd7d2de104363836
+size 1682260896

model-00094-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2caa8ada76cedd00a94ad2b5a4588c1368a372bc99add01b5748fd3dae4011
-size 1737704144
+oid sha256:b4e30e31ffe517e43138aee025a41b99f4d51088ea7051bdd0099758d0bbd2ea
+size 1682261024

model-00097-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cf90375e2fc4b3974fda949c1a557e95a7ac5505aad9676cc07b781fa86962
-size 1737703864
+oid sha256:5ec1eec1e77f187177d357f1356aa85303b247cadb1eb6dab9f8f79c40bd310e
+size 1682260752

model-00101-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c345cc5fe338a7af7c7305bc86c48fe29c69e485174c20ce4dc65003c6b66544
-size 1737703992
+oid sha256:0b37e728dae61af0239a92e43d7264f2feace92b0db887094099823847fef69f
+size 1682260872

model-00105-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bd59695f0fda2fbf3b4901d72829949015d69f1f150854800ae859e21dfce8a
-size 1737704120
+oid sha256:e1c113c165c316ae88b0a7b3463536d057701b3f7e14e905783a5db86ce083de
+size 1682261008

model-00108-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3cd8402fae5411f224ade006916db6e3ac40cd4ea17482c3491a3a4858dc5d
-size 1504249752
+oid sha256:83ccbb66c29c24cb03a251c83510c9a649d2b9d22e7e89b75ba6beff61b5ef64
+size 1448806616

model-00112-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791955e071af8f61889e06e8953e7debc7eb97c5e0add748230a7e84b4191209
-size 1737703952
+oid sha256:9469e434fa0342336d5b2e329f9664a066b672171ee0d2c6a6f437c26837f507
+size 1682260840

model-00116-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afaf09ea013da6ba7612a759fc0827cfe05c11b6356f841c3a2e9f246d43b518
-size 1737703840
+oid sha256:3193be43befe2da90df59608f55674c2162a6ecfb51bca07b5600203419b9051
+size 1682260728

model-00120-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330de3e9ba98ab236b81e42ee5df965c3db720773eaced3b23ea0afab6db4fac
-size 1737704184
+oid sha256:49f276721893ac4b2c3f130fbee66959c729f568571e25ef37a772143975006d
+size 1682261072

model-00123-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eae656b6818f3bd54985b642a20cab861a52dceedcced0a9c4d1a96fbd21597
-size 1737703928
+oid sha256:1ada0068dbc11c6ab61ddc3461e4952a1e584f25d483ee8c37a8d933576010d2
+size 1682260816

model-00127-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5174ea701966fb6fe6c6c988eef665fe9ad39c77540567908a12cb567d463da
-size 1737704064
+oid sha256:e163d99e1677296b904fd17df746f154b2fb5e41a7a60715a93667114b31d449
+size 1682260952

model-00131-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da7f4bd19d8bf3b1ee16e590b2a3afbfda078173a0f798a0ce1eed23697dcea
-size 1737704192
+oid sha256:a5d5d6210a3d237ebd726fc2a9a4d486eeaa2b8dd8c0f3b3ce7c6288cb13bea1
+size 1682261080

model-00134-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c432d0919dae37ed4376b16d604dca6f950a9d01d9fb78e60819fcd00a2859
-size 1737703904
+oid sha256:afa0218e000b727b02f49ed91d351f35c5249939c190f765ebe5411c25a2f0e7
+size 1682260792

model-00138-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67fe316ec47c64166798212128cb54f0bfd0f8d85d6660d352e3df5d9bc5221a
-size 1737704040
+oid sha256:0c2cbed6245333571e089fc7d034faf0f84492b1741b9080a73340edc8ac6005
+size 1682260928

model-00142-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccfc435a5a4f437bc37e0e07b2215e0f0035284d2edbf6e664177a35f816387
-size 1737704176
+oid sha256:cd930b09b631bd569888a8c110fbf7051d6e63e4990c1e929a94c950b13d5adf
+size 1682261056

model-00145-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3b46c5d8e94efef2368078c43053ad92f70e50e7717563152550ead89a185b
-size 1737703880
+oid sha256:815f57c811220dc80408eb9f3631a7e39a950e4d4a071b532aa027f27869aeca
+size 1682260768

model-00149-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8f0ddc92572885888859cd931bfd9973c0962a9410b3021d539ea48dda0b77
-size 1737704016
+oid sha256:1e48d30fccc583239d7889f4ff3954980c3e21be4152a849c7c7ec1d9d03a861
+size 1682260904

model-00153-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3043bb35774665f9c6a24fdefb26c69c78afe90782ee02faec89f8643e2d03d7
-size 1737704144
+oid sha256:c3edfbbaffd8736739bbcc329a64120ac10b1870022ad636cdc18dc317e2c5fa
+size 1682261032

model-00156-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fbab3a720a1316719dcb806f4df3fad08fc68b7bb4b6e531c79ff7ce593a53
-size 1737703848
+oid sha256:12f73ca5e501b241930ade2ae457ea7aacfa16438c74b2370d0ff323114ec4e0
+size 1682260728

model-00160-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacc6dd6de00bba38ee334a0dc333249e3607c25011d53db57396a5b51701ef8
-size 1737703728
+oid sha256:04a295a181f0d879019b6c10537ea89b5a02e4b841589d2586ea74f584cdb901
+size 1682260616

model-00164-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124b46932db66c81c40baa74b13006bd2fb0aa0982931faf53e738b72754469a
-size 1737704120
+oid sha256:69b81239538f757d0580c40a9bf3ce003917af873271d98ce28191ac5ae29613
+size 1682261008

model-00167-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77afcbea7ec5ac149035df1239296505f85b593f009edc310ec470c7af59655
-size 1477510064
+oid sha256:5c3dca1b5a95cb791c5d485f2f94973638de8060cf5f4d4dc6afe4ef8e8ae6e4
+size 1422066928

model-00171-of-00282.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:606d62a76680d637be5cca50df5d9db924ad682125bab09bbb7dc28c8fcb8ca6
-size 1737703952
+oid sha256:51214bfed6a6953169cc552f78c5aeb71c852196c1eecca2b5b298e1a5a7db1b
+size 1682260840