Upload folder using huggingface_hub

config.json

@@ -28,7 +28,7 @@
   "norm_topk_prob": true,
   "num_attention_heads": 128,
   "num_experts_per_tok": 8,
-  "num_hidden_layers": 5,
+  "num_hidden_layers": 4,
   "num_key_value_heads": 128,
   "num_nextn_predict_layers": 1,
   "q_lora_rank": 1536,

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f996c13c6fc8789fb6c31687efe13407d0a5de3eaef5936755451a3f46c705e
-size 2147050520
+oid sha256:e13f571e3ab3c0809e0a8095f996f79493696ea492d39167d5a192198fd84a0e
+size 2117678760

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2b067446938fc82071aba70282ec97a7b238ec2e748c1b056e9ea3a20d3d40
-size 1578895112
+oid sha256:6fc45f82c180cb9e7cc22d58d087cc211d779d9dab4b2331d855db927933b861
+size 1255617808

model.safetensors.index.json

@@ -1,51 +1,71 @@
 {
   "metadata": {
-    "total_size": 5579274816
+    "total_size": 5226637824
   },
   "weight_map": {
     "lm_head.weight": "model-00001-of-00003.safetensors",
     "model.embed_tokens.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.0.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.0.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.0.up_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.1.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.1.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.1.up_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.10.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.10.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.10.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.10.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.10.up_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.11.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.11.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.11.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.11.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.11.up_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.12.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.12.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.12.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.12.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.12.up_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.13.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.13.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.13.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.13.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.13.up_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.14.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.14.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.3.mlp.experts.14.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_scale_inv": "model-00002-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.kv_a_proj_with_mqa.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.kv_b_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.kv_b_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.q_a_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.q_a_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.q_a_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.q_b_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.self_attn.q_b_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.0.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.0.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.0.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.0.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.1.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.1.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.1.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.10.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.10.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.10.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.10.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.10.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.11.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.11.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.11.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.11.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.11.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.12.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.12.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.12.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.12.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.13.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.13.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.13.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.13.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.13.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.14.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.mlp.experts.14.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
     "model.layers.3.mlp.experts.14.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.3.mlp.experts.14.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
     "model.layers.3.mlp.experts.15.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -122,124 +142,6 @@
     "model.layers.3.self_attn.q_a_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.3.self_attn.q_a_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
     "model.layers.3.self_attn.q_b_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.self_attn.q_b_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.0.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.0.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.0.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.0.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.0.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.1.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.1.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.1.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.1.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.1.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.10.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.10.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.10.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.10.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.10.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.11.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.11.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.11.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.11.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.11.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.12.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.12.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.12.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.12.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.12.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.13.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.13.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.13.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.13.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.13.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.14.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.14.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.14.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.14.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.14.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.15.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.15.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.15.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.15.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.15.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.2.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.2.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.2.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.2.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.2.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.3.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.3.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.3.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.3.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.3.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.4.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.4.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.4.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.4.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.4.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.5.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.5.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.5.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.5.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.5.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.6.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.6.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.6.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.6.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.6.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.7.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.7.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.7.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.7.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.7.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.8.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.8.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.8.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.8.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.8.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.9.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.9.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.9.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.9.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.experts.9.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.gate.e_score_correction_bias": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.gate.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.shared_experts.down_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.shared_experts.gate_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.mlp.shared_experts.up_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.kv_a_proj_with_mqa.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.kv_b_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.kv_b_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.q_a_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.q_a_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.q_a_proj.weight_scale_inv": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.q_b_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.self_attn.q_b_proj.weight_scale_inv": "model-00003-of-00003.safetensors"
+    "model.layers.3.self_attn.q_b_proj.weight_scale_inv": "model-00003-of-00003.safetensors"
   }
 }