Upload ReasonEval_34B

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/cpfs01/shared/GAIR/GAIR_hdd/sjxia/reward-model/prm800k/llemma-34b",
+  "architectures": [
+    "ReasonEval_34B"
+  ],
+  "attention_bias": false,
+  "bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "score_dim": 3,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32032
+}

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f064ef9dffb120307dfb0fff48658656875ed9056ab6de08f129e4918f0d5bf
+size 4421912160

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be78f21d41620290422519689aacf7ea6e8db8f07a2595be7025a8354fe10ca
+size 4932634200

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fab0bc75a44a1913d0cc2d924111a176a021672d1ff93eba0776cbe0e86bae
+size 4815128272

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8175ced36910d997bc94aa36202e4d1d8d67dd3f866030cea2fa31daa0341d04
+size 4815194040

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3c5fe49084727025b0bc8d0f5a62de1d8aff480e5549b3b0a4c66c8a617b43
+size 4815194040

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f711c0035c82315844d24430a1020792ef2b0bf8b5e0dc5b2d7e4140fd652c
+size 4932634200

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65593f37ed54b7c8bdc3b0c48b6d24814005bfea52fb3443a218cb83f098ed16
+size 4815128288

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeea2380969003828eb6bc30fceeb5dd27d5db341989de0a4f6448e2c2c35a5f
+size 4815194056

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f206185a5f254bea94a9caaa36885674930962dd9b8f43c31c48789b7c45d5
+size 4815194056

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c54ad63864d19805f4908067fe8233c5e8a64683887e9080b9d88249530f720
+size 4932634216

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acddcc4af14139972f5167d0d2a1a4d38ce6fdb910fab9348efa5b602d20c918
+size 4815128288

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b288b138d834a806e89f53b6b829cf5ff2a247775fb9481e1105605cb61cf9ec
+size 4815194056

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105188255e82220186f3ed6f21ccfca6fec0bfc10b23c7476e3dc88a1cb43725
+size 4815194056

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20297cc7269c6177f02b526c4102ac01c34364479b6427bb12aea9bb7b9f093c
+size 4932634216

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e695d953a18d100dd5418d729eaeb29eaf2bf485f1b320d567d95168fd1961
+size 4815128288

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5783169466279ce61bf5b084401993f37a5afb2ac73b32968aa7306f2195f4a2
+size 4815194056

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ea107775eb1155d8ee2ac1f7b38ab9082298fa151445e4aac441e4072979f3
+size 4815194056

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ed395e29730d441c69173b9348b5942e1ed3c178ea01cbfe36e9b8bcd8b1a1
+size 4932634216

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fa7d7c216741c8a7b4f0321d397675479ec66a7c10cda668e287349d130254
+size 4815128288

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af7226124b5fe07ddd738e0927c1e412c695d666335c45bc5a2d91eeb66d173
+size 4815194056

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759ce7d521a1d818c680b3362aac819d5af1aa39a83cc5b85673234de2158ff9
+size 4815194056

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05fd0108cf1b7e33d74a818d4350ff4f6da35f8c0e1ab8dfe5dca0faffb076f
+size 4932634216

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0516b32a6141d4febe667634ad50b9f0fd29992a9652c43dae1bd798a0977514
+size 4815128288

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5fddfbc8eb871250782ec03a46cde9ef5f8a9b50f704e0087c1cd56c4a69682
+size 4815194056

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdfea48bde8787bbf5cb0731e1361089465655ac53138bb5fb9f4027f8f342c
+size 4815194056

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ba01536282996ee9e548de4a1da20947bba959d6f54ed4207716bee2149271
+size 4932634216

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87780b1767fc8fe21d375f829467bc40babcdd5a636fd04045ec0db5cf70d586
+size 4815128288

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5f6d8517310d5480887be5119ea8f8278ecb4ae4ddcc50b51bd85fb39eaf11
+size 3489924664

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 133928452096
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00028.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00028.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00028.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00028.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00028.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00028.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00028.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00028.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00028.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00028.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00028.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00028.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00028.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00028.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00028.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00028.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00028.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00028.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00028.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00028.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00028.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00028.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00028.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00028.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00028.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00028.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00028.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00028.safetensors",
+    "model.norm.weight": "model-00028-of-00028.safetensors",
+    "score_head.weight": "model-00028-of-00028.safetensors"
+  }
+}