Finetuner.ai deployment ID: YOT3R_GWS94

adapter_config.json

@@ -20,49 +20,49 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "model.layers.1.self_attn.v_proj",
-    "model.layers.2.mlp.up_proj",
     "model.layers.1.mlp.up_proj",
-    "model.layers.4.self_attn.q_proj",
-    "model.layers.1.mlp.gate_proj",
-    "model.layers.5.mlp.up_proj",
-    "model.layers.0.self_attn.v_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.4.self_attn.o_proj",
     "model.layers.1.self_attn.o_proj",
-    "model.layers.5.self_attn.k_proj",
-    "model.layers.2.self_attn.q_proj",
-    "model.layers.5.mlp.down_proj",
-    "model.layers.1.self_attn.q_proj",
-    "model.layers.3.mlp.down_proj",
-    "model.layers.2.self_attn.o_proj",
-    "model.layers.3.self_attn.q_proj",
-    "model.layers.2.self_attn.k_proj",
-    "model.layers.0.mlp.gate_proj",
-    "model.layers.2.self_attn.v_proj",
     "model.layers.0.self_attn.q_proj",
-    "model.layers.0.self_attn.k_proj",
-    "model.layers.0.mlp.up_proj",
     "model.layers.1.self_attn.k_proj",
+    "model.layers.4.self_attn.k_proj",
     "model.layers.3.self_attn.k_proj",
-    "model.layers.4.self_attn.o_proj",
-    "model.layers.5.self_attn.q_proj",
+    "lm_head",
     "model.layers.5.self_attn.v_proj",
-    "model.layers.4.mlp.up_proj",
-    "model.layers.4.self_attn.v_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.2.self_attn.q_proj",
     "model.layers.3.self_attn.v_proj",
-    "model.layers.4.mlp.down_proj",
-    "model.layers.1.mlp.down_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.5.mlp.gate_proj",
     "model.layers.3.mlp.up_proj",
-    "model.layers.5.self_attn.o_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.3.self_attn.q_proj",
     "model.layers.2.mlp.gate_proj",
-    "model.layers.3.mlp.gate_proj",
     "model.layers.0.self_attn.o_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.0.mlp.gate_proj",
     "model.layers.0.mlp.down_proj",
-    "model.layers.2.mlp.down_proj",
-    "model.layers.4.mlp.gate_proj",
-    "model.layers.5.mlp.gate_proj",
-    "model.layers.4.self_attn.k_proj",
-    "lm_head",
-    "model.layers.3.self_attn.o_proj"
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.1.self_attn.q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c8ca7c1818278409305ed2719c3a11e0ba26d9470bee1f5089102218641274c
+oid sha256:4dcdabedbb78c575ef6a62db49de3015a94bc5a2b524ea738393363e64b95591
 size 38959168