Upload model weights (#1)

- 976d768a147e864ede9e4218e1db0830b058898f68f4d807e33ee55e6821df28 (b1d98f4503863dc8f2ee954b3e5dac1e8f3de968)
- dbf91073e1609249f7ac6864e82b6c1d70027d83726b989fb79b1d4ebca58023 (1d147a4cf74c5d8394886494b153c656ec689c61)
- d3648c28c2268420d17a591c0fb34bae1d0df1a1e67843dfa780b8909c50cf64 (3df2d3468f38c7dff5b580e1ea087dd4a5702d59)
- 2b14fd6d4c2a2f2c68704c3dab8aef6af6d42f1b165563ecdfbfbb34ca308364 (fe67aa9d34ee89d6d8f4760ce8ea4daa6f964e05)
- 01c457b8fd32ebd62db7fc31d43cc64ea012d285fd0cd34980f970e1df9fb427 (9244336be42638f1fffcac73f3cc624b68eef9c7)
- 5f02e82a21a1dc26b308afb13e2d7304fd71a880c0d548d077f59cb5fb07724b (8814c81dcfb08d09bb3479317c20cc73e4d7f886)
- 7dee55a190eb61fe19dd53573e7f43cdce7a51093b302db7fd20a055fdf8b687 (8defeb7ef3dd537dc4a64bd74c9cd3956d74cc19)
- 769b0c303c2bc26133c3b791a2aeffdedacf34fa3848914e212ea1f7cd604a3f (a79419c0f9327741e43b6a5603b6f7296c11f545)
- 0fa34c583a2d02ba6772e98e590ce9a45fa23cb997362b4a7ef38c17726272f0 (0416c24fa3f06528062333400aa2f1dd15406e8e)
- 30ab78f90260e3f111d42026ba8e7d8c92850fc7d40cbad5694d6a0820c97856 (bc1559c18f8813d77ca90f9297a1e824f2c2a74d)
- 9546b50bd4f828a38cb4bc5abf746f684b821447a514c93b5a4ee21e082d1d28 (825937a8489ca512b1cbb80fb5769755ad5066ce)
- 76b5a6c632628e1055a05d95377882f9e544773353395873966822243646aa0e (f4299d917f6643d03dd228f2d7b6127db0c4bc42)
- 802edbfa1d8021e56b2eb5d6c3f7ed40c755c0e9467d6ddb3da63375ad29c990 (1f36d7e58731afc4b6cf13258a9a7abd806d27c0)
- df4084ca2050197f93706fd447bc79cf12b826b5d294b0b5f9b4a08025f7f5e5 (9d77abfbfc8aafbdb1ea0aeba7662898fddd5515)
- 05662ae5cbc5bf4d296a31f9dd0c38249c7e7d5d72843670e2b88ef2b3d20183 (8caafa0de30d578ccf187abcd3af9ccc971c7328)
- 5785d1b564254f9bf66a6970bfd23b98f460515ed87882e9058396770604435b (47d3bd0751c84316521dbac14c71b1fb17ba1352)
- 88eb34ba0c48a009d72dbc53f30168f61657a253a29f534395f8e4d256ccb8e7 (c924985d5dea17e63aeeb08a00558b69b706c92e)
- fd830d2c2664b1461612fb968be15250aa9cde3334347778b575d09ebd0c438d (e31d1816f79b701d1a6d2b2167a36b46f90b4f17)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "midnight-rose-70b-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

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": "4.36.2"
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4c148f62b61eab3a31d657aba4fbfde4bba77887b67fd54034a0bb9048d005
+size 8141279976

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1bfd06be32a5c6b2d8e0f21f104d126852eceb7fe1ddf680566893f5b53f75
+size 8086787016

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000bd3b393c33c3a6fb5eebcb5ad085ce736601b397ddcd8e83aff4f0ca91cac
+size 8254558872

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8821fbc114b404bad31053b32fec2e0494871b826cdc33661b81aed12fc1d341
+size 8086754072

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e6dfc24eb057eab336bb35834a53aac9c3bbc31c6f8022f89708e11d5bcd60
+size 8086787064

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fd0a55fdb3402efddc239e47de19672a63565cc8980058ddaf93fbfc4ef03b
+size 8086787064

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddf1c1f943649cf582223b5d7c2162b96b96df26ff0298a8370e75a029e52cc
+size 8254558872

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fad500222e57ec496b41c7aebacaabe54467cc88fc3dff7749b5ae2f725d773
+size 8086754072

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dedf0d5528df3310b392f4ef291b1a082053e3c1ff81044d5c68e8e1d9e8dcdd
+size 8086787064

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1c67687fe113a94972f27dbaeb827a85b4bcebb17e703c53e77587a6c75b31
+size 8086787064

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d821ff601a4ef0da39c7389fa929e6f7a7edc9e1b7f5baf58ce2e3400828726a
+size 8254558872

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbb88eec0d6d5a7a45d54e930d731c8c5bfef10890ef9d64fe8cb0f6649b130
+size 8086754072

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25bb7282570c2bb6e36994979d1f084daace897274aa202a69e96610d34d41b
+size 8086787064

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410e9002573dda8c81b1842405e7fa20a35e74e8fe18fe7598b6fe063a1e4438
+size 8086787064

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b0d3ad14e3fcfde279b112382e9c563f9f4d551f01a769a8caa9b1976d050f
+size 8254558872

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1d177c43ec62c7c6f8eac673d758b4b10b8409ba51cc74f7e87f45f8d6f7cd
+size 8086754072

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19820512cd548d06af94c6b53baeb9c2632c010203e5adc6a8d7494d6a94694
+size 7839339120

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 137953296384
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.norm.weight": "model-00017-of-00017.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}