feat: reupload weights

model-00001-of-00004.safetensors → model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6354f592f4f71f22bfff9d701bea06ddcfc3eff08007eb5f229f17b770b3b4
-size 4981626968
+oid sha256:e0e2d6673950aef18051379de3f8b9ac71079213a2396ed41eaad5f3325317fc
+size 4795637544

model-00002-of-00004.safetensors → model-00002-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e63137114fc34e3c148c251810c8a81d65e3faea8f38963caf0670f2e634d0
-size 4949470904
+oid sha256:c14b9b0619077a8a40c86cbce9d22d57e65ebf13ab4b847bf870846d66e748f4
+size 4832007544

model-00003-of-00004.safetensors → model-00003-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ba4a26dcf8d0989f1074b50d917338751b05d020b940b9f69ba86601c7c7e6
-size 4915916376
+oid sha256:b03fd3bb595b5bce41d77c48b08d39fe6e064036e1ca684702c010cb7876f954
+size 4999813200

model-00004-of-00004.safetensors → model-00004-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8f3b260d5dc3813ebdf30f768ed733b71e47e1ca36093f99bdfba57f87a722
-size 1006692968
+oid sha256:67faaafa1cb268d84031a540951a4ae69f96c5b57b29562bedd9efe18c9f0a6a
+size 4999813232

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4290ffc52ad6a3bfc4b652ce629ca08504d607a24ce2688ce17c6bfc6a09c56f
+size 4832007592

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b47969386a099ab2486cac4d892ccea975a6d97ccb3c603038b60d46592b7a
+size 4999813232

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ada5ca6cf7bd855bf6953c89e2bfb54b9b1de7829cb8ca48fb7139b49e5d63d
+size 2231487200

model.safetensors.index.json

@@ -1,493 +1,493 @@
 {
   "metadata": {
-    "total_size": 15853649920
+    "total_size": 31690522624
   },
   "weight_map": {
-    "llm2vec.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "llm2vec.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "llm2vec.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "llm2vec.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "llm2vec.norm.weight": "model-00004-of-00004.safetensors",
-    "nllb_encoder.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.fc1.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.fc1.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.fc2.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.fc2.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.final_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.final_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
-    "nllb_encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
-    "up_proj.weight": "model-00004-of-00004.safetensors"
+    "llm2vec.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "llm2vec.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "llm2vec.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "llm2vec.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "llm2vec.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "llm2vec.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "llm2vec.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "llm2vec.norm.weight": "model-00007-of-00007.safetensors",
+    "nllb_encoder.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.fc1.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.fc1.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.fc2.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.fc2.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.final_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.final_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "nllb_encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "up_proj.weight": "model-00007-of-00007.safetensors"
   }
 }

modeling_nllbllm2vec.py

@@ -98,9 +98,7 @@ class NLLBLLM2Vec(PreTrainedModel):
             )
             nllb_last_hidden_state = nllb_outputs.last_hidden_state
             nllb_last_hidden_state = self.up_proj(nllb_last_hidden_state)
-        if self.training:
-            # Inference mode otherwise yields embeddings that cannot be trained with
-            nllb_last_hidden_state = nllb_last_hidden_state.detach().clone()
+        nllb_last_hidden_state = nllb_last_hidden_state.detach().clone()
         outputs = self.llm2vec(
             inputs_embeds=nllb_last_hidden_state,
             attention_mask=attention_mask,
@@ -396,8 +394,6 @@ class NLLBLLM2VecForSequenceClassification(PreTrainedModel):
         pooled_logits = self.score(hidden_states)
 
         loss = None
-        import pudb
-        pu.db
         if labels is not None:
             if self.config.problem_type is None:
                 if self.num_labels == 1:
@@ -446,15 +442,18 @@ def repl():
     nllb = AutoModel.from_pretrained(
         "facebook/nllb-200-distilled-600M", torch_dtype=torch.bfloat16
     ).encoder
-    llm2vec = AutoModel.from_pretrained(
-        "fdschmidt93/LLM2Vec-Meta-Llama-3.1-8B-Instruct-mntp-unsup-simcse",
-        trust_remote_code=True,
-        torch_dtype=torch.bfloat16,
-    )
-
+    # llm2vec = AutoModel.from_pretrained(
+    #     "fdschmidt93/LLM2Vec-Meta-Llama-3.1-8B-Instruct-mntp-unsup-simcse",
+    #     trust_remote_code=True,
+    #     torch_dtype=torch.bfloat16,
+    # )
+    llama = LlamaEncoderModel.from_pretrained("../trident-nllb-llm2vec/data/model/llm2vec_llama3-1_unsupervised/", torch_dtype=torch.bfloat16)
+    model.nllb_encoder.load_state_dict(nllb.state_dict())
+    model.llm2vec.load_state_dict(llama.state_dict())
     ckpt = torch.load("./step=20000-weights.ckpt", map_location="cpu")
+    model.up_proj.load_state_dict({"weight": ckpt["model.up_proj.weight"]})
 
-    model.up_proj.load_state_dict({"weight": proj})
+    model.save_pretrained("../weights_new")
 
     from peft.mapping import get_peft_model
     from peft.tuners.lora.config import LoraConfig