Upload Qwen2ForCausalLM

config.json

@@ -39,9 +39,7 @@
       "model.layers.2.mlp",
       "model.layers.3.self_attn",
       "model.layers.3.mlp",
-      "model.layers.4.self_attn",
       "model.layers.4.mlp",
-      "model.layers.6.mlp",
       "model.layers.11.mlp",
       "model.layers.24.mlp",
       "model.layers.25.mlp",

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8231319d72b4fc1c981edaa8cdc5186c7d453dfeba29e3d2570b6af7d872796
-size 4995769972
+oid sha256:d89951edcbded32eea6718bf5957114c7151be76c8be277a381fa98f7105209b
+size 4967113023

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5beca751f42e159960c6753202b9f1e4a50e55e45bd32f86400de343d17ac01
-size 3835794652
+oid sha256:32152fcce250c61031324ce54a600de4e483becc307df492b0c910314b5cf2cd
+size 3518593782

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8831440744
+    "total_size": 8485578781
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -155,26 +155,26 @@
     "model.layers.12.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -182,12 +182,12 @@
     "model.layers.13.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -202,53 +202,53 @@
     "model.layers.13.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -256,46 +256,46 @@
     "model.layers.15.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
@@ -826,11 +826,31 @@
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -880,8 +900,23 @@
     "model.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",