Upload CohereForCausalLM

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./hormoz",
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.125,
+  "max_position_embeddings": 8192,
+  "model_type": "cohere",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.2"
+}

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df3ac5cb199d7f80662c2a2b497d23afe213475dbb353e8c9490ca5e859c5fa
+size 4194304136

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9679aeeff876f762fb8a594f760c0fa89dcace9a8361850b5e43431362bb067
+size 1912637696

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdd5d1ac9f4455bee33deb7dfbe2fa8777c862fefecf33cbec3e13d43288adc
+size 1979746216

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428d094194c25306eddd3ed54bfed2352cab11a0d2f46e7b181e2fd70f05e14f
+size 1979746208

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e489507e67e4ad72346a68c5eedbfc8da15cd233856fef464190f86fad5e2d0
+size 1979762704

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0633977bc99e6afcdbfe1853d3b28e630dfb17ae27714c55d0cfd41f9580ba61
+size 1912637704

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9e51370ef5cf549e829ae47f9cc8edeee1c82d29291d7881eee3e8fec356be
+size 1979746232

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1c93552f732429a248af84e91825b73b81de28bdd3661db17c61b9a28b15c6
+size 1979746224

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b63846ba1cb3d2d97a3224eed89022ebc86382a50347f7c4ac5d1635d1678ef
+size 1979762720

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e0f9a116e867fc3a3aae119455ab90a0c12cda3e599b3701e46bdfe1f99d28
+size 1912637712

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2480fe94fea195d1d558b9b3ed83f51164de8de792c021401d052d2324022153
+size 1979746232

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be90e91a43ac57507a6520b61910f7d2886dd3d8f939953bd887359133c9f2e5
+size 1979746224

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b8253e1adb08b433c4e9221835fc88930a335aa345256482f6a39f7968660e
+size 1979762720

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709c5e11c176f2e1933d83fbc091f713af28904618c79c841c9734d06b7decda
+size 1912637712

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023ff8c44cf9f57486bd54f37bac93133c0b1482c245890aa33f3e2702cf4b72
+size 1979746232

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed4b3d5b676808b47fa7302b7f6bde2eb0bf751067d3cb2d5a6e8e5a5b7f7c7
+size 469795264

model.safetensors.index.json

@@ -0,0 +1,265 @@
+{
+  "metadata": {
+    "total_size": 32112132096
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.norm.weight": "model-00016-of-00016.safetensors"
+  }
+}