Upload LlamaForCausalLM (#1)

- Upload LlamaForCausalLM (9c49232becdf4548be4438b1f00c4133957ae623)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "01-ai/Yi-34B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f40e9fb3e2ddd985ce371923a27cf651c39c26160ee60e55582952df389b492
+size 1739588416

model-00002-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f346a9a467db03ebc7884325b4f2420db774740da9c1365ed30d5dc32acf04
+size 1937827776

model-00003-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283188a4a72297107e368a89883fcd71ca095ab11435780fbfb0d7a397a845c6
+size 1937827776

model-00004-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579b487e8a0852ef2369fe6b84e0d37e9c2afe688fc81fbd5adc3a6318ae8c26
+size 1996547680

model-00005-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ff6d02037a24650bf07e7d58469c3a042af93331df2a53fb07905fae4e5487
+size 1937798872

model-00006-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db17842f263b0b725fe758d5b69e3b718030f2dd16f8fbe5ee80753411d647e
+size 1937827776

model-00007-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21554c4c4a26eb91d6b2a4f8a6e2abaf176be46a3f306682e719ffc6a56995a
+size 1937827784

model-00008-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad9421ce8590e5cd0db41ca1e7b8bcef4fef4b3ac780d472db224c9b20803f2
+size 1996547696

model-00009-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a9877151c4cb8fc4d541e14f6815133d5e214cf3c99620445c7f7a5b43b079
+size 1937798888

model-00010-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7cb3927206fe72ded3317e59cc3a9e4c5ead2dac7419b2169b8c3dda8385e2
+size 1937827792

model-00011-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b5e0c337de181d764d48305f0cb245c9c4863b6d4c1a6e27a41f80a647565a
+size 1937827792

model-00012-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37d57247806cd75115a9c7655fad227c16aa6ba95790a9f612340c76355a4af
+size 1996547696

model-00013-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebdd3527047f62ad11862f7c0107387beb3a2eac57c46384561d265171934dd
+size 1937798888

model-00014-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07f82415871a7b0532809000cccd0918432ed96772832b217ca47056775cfa9
+size 1937827792

model-00015-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b78dccf9ae7d3b2739be01f64d104a7254859328348d79f551f126ed9f5925
+size 1937827792

model-00016-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca8ca9810744e93b8acd895e55789f428f11d1d49455493356e41b80498014e
+size 1996547696

model-00017-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168a8c23385af7adcb6ecfc5ca5c8abd58dfe6c8adcbd9e878a47416884857d4
+size 1937798888

model-00018-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f977c3ca15550a16b19ef2dc62b404e2f78ea9a27d251775fd49f4a7b60cd95c
+size 1937827792

model-00019-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0523e2c5c33708834a3b2c3993b9007d0fcd6f301165abc0ed2eec2835bcdf
+size 1937827792

model-00020-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15891a45a8221f0e72c1de22c85147e2e3990c51dd1f94f8bc890e6e60f12fa
+size 1996547696

model-00021-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3780e78bdcd9f4c0f0832b5c504cb53838c3941dd33e4154479bc27e500453
+size 1937798888

model-00022-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c69b8963b47b6872fffbd0eb8751cdf59150cc167373a44d63786f5837555dc
+size 1937827792

model-00023-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91288fbd0c69473d9d0a8a553b5cb2a590bdc11533004de4d42f931bfb877d1
+size 1937827792

model-00024-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16b381d2e474bdb39ce88c87f5b4e9b295023f2eb3c737a1ff4f539eac5390d
+size 1996547696

model-00025-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ca539f2ed6cd03e15a4a7b288031573266f954d6d1eeb96c6389fe958f25a9
+size 1937798888

model-00026-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f092f0d49cd95b066fcf5d8692e9b8e6d388bdb2975811d80a9e308583849311
+size 1937827792

model-00027-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae822d4dcada24a6e63a720f5a54548c815000cd2e5204682f411839137fdc35
+size 1937827792

model-00028-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a479da207e93dbd08be140c7403fd394b071ea98e6b48f96577a657235e142ec
+size 1996547696

model-00029-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2517fe108aa09a2bab95188e4697c1c728c4721bd5f5604ada971fc18b9e5e1e
+size 1937798888

model-00030-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14409cded3351ce4640d0bca63174d2ffe3d82714f4afb704158b3f489c7756
+size 1937827792

model-00031-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d6764a28e3ad580cbab01f4cd6ee480e2d9e7fae10778aeba6d261fde9d506
+size 1937827792

model-00032-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810f00f21eb2197355939680fe81b2ea2ecbdaf55a02ad03f6b01b9777cb66d8
+size 1996547696

model-00033-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35bc02f2544cf1851536383f3d7542c834d9f3b85f54a8929d69c51b167dba0
+size 1937798888

model-00034-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7171d32a75031d800c9a85b45af39e6d829abb50b2ad73d415efdc003f5329b1
+size 1937827792

model-00035-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8111ae3f5b4142f7a198ee2c5a1ae296008e33691be7fb11cc953fe054d5420d
+size 1702960720

model-00036-of-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18622e7b74d4645c26e592e75c7d3d2b83d875eaae1e8965d76f7f3de933528f
+size 917504128

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00036-of-00036.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00036.safetensors",
+    "model.norm.weight": "model-00035-of-00036.safetensors"
+  }
+}