Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.model.v7 filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 12288,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 96,
+  "num_hidden_layers": 67,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.2"
+}

model-layers-006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b7b965bf1c19c55801fe17b8bd910de0d2be1aab876de25767843b313acbd6
+size 2768290840

model-layers-008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d2bc776add8d99ffa5227610982f73d70847c24d0db168ca45f0a811f1f71f
+size 2768290840

model-layers-009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09937d318614f4f35fec49da8ec2b60cc6d364ac0d942c81039ca7966b4f0c98
+size 2768290840

model-layers-010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82aa11c24f0a3a1fcce344ca9cda3224f9e900f4aa9662486dff61a82f299fdc
+size 2768290848

model-layers-011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f29b61995853cd147abf57b53d08e7e2842126d818846e2b49a2dbb4d5e0a86
+size 2768290848

model-layers-014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbab9f15cbb718339a00bb7cb41d1252e3a2461bd1c231ed7b20ab7123e8b90a
+size 2768290848

model-layers-016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768c3711e3d4607a48c25037353af503886f54ab38c045a398af38c230ec48a5
+size 2768290848

model-layers-020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d285724ad0a1ea32ca418491598ddc79b237081e82eb04fdcf867c01cae3ff6
+size 2768290848

model-layers-022.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5da1efb0353f24c5554d5590649e1feb4b1cf55fdcd0f371edadec5ab9c2c8
+size 2768290848

model-layers-025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38cc296241780578c62e2d6ff67a42ae8ab95f2c5bfd47cce51b3a2085f71d0
+size 2768290848

model-layers-027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518b49034a229d2f6608e7bb84d96161f19a5bfba53e358e5b0a8b52a220ff29
+size 2768290848

model-layers-028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1959254ede8a510f5494f0f41b90ac08786aedf5b03a9cedff1d87361e0a1d8
+size 2768290848

model-layers-031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3584bc1c0fda7fba671a7a0e61275308c2b937a2d67fbe897b121fd76541b62
+size 2768290848

model-layers-033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979f35f5a19117e4e12e774ba4fc83e325ae7ca8b69b21758e550027a2520d8c
+size 2768290848

model-layers-035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc382bf0f832f6f49f5580ae7dfb17e2fb0ca8fdb2c9c0a879cdbb5154766d6
+size 2768290848

model-layers-037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78705f8ed146c3bf3db788ac7ea0b4fc1cfb4231b38facbdd77a23e3859f5d1
+size 2768290848

model-layers-038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf5c33726bbf70145a90f5eda17e68334652ac2d3df5335f90c5763710ff028
+size 2768290848

model-layers-039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236272b46779e669df9e15208204315672c23ede50e314e87119a432a9fc1091
+size 2768290848

model-layers-040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5e323193360c6c2c9cc7acfb419bbec1d0336aa110ae636d3fae7ae42b708f
+size 2768290848

model-layers-042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416db14f42fe346daff48657c37602fc82c8b1de0f6ce5135ad836dab43b553d
+size 2768290848

model-layers-044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba06e304623f4abce4be593aa58546d14549cb69ab00431e754d0a18e92e4c9
+size 2768290848

model-layers-046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d13f72e49b6926b65cd2bad95f6a2888165023f90c7a49d9e731dbf739f487
+size 2768290848

model-layers-047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6409ee582aeaaf05ab50f66277bf1a46834c298bd763918f89714a24f7495f3f
+size 2768290848

model-layers-048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6391869404142e324df180254cdb27806c1a44423302409ea40b8e52c20880
+size 2768290848

model-layers-049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d3c8329d245903bf3b3fae58e7b58d91b5b769f1c31149dfdaf62fb6674799
+size 2768290848

model-layers-050.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b338ac64f53b58b6c19d305c4da7c918f84a6addca0cb4bb5091f42bc66b12f2
+size 2768290848

model-layers-051.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fdfc76b0c5b8c97138e37c3d022b9b482be47d26fd523bb265e92bf6e734ca8
+size 2768290848

model-layers-052.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767c9ffa2ae663dae5881883557238c57162c970465b5d60778d81ec88e8b293
+size 2768290848

model-layers-053.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc39a07617d6ef8c302dccab633a28571017096836add9f9d763fdde7eb97ef8
+size 2768290848

model-layers-054.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb6ad7145e28d7881fa20f0198478678f73b9e8f154f84bb7ce28bdf7bb2909
+size 2768290848

model-layers-055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50910e8790753d050b0d410049bc858536a368f80b2101783e5536a6e94cf58
+size 2768290848

model-layers-056.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8060855ae305730de20dcbd444bbe0299b93741c3201f818f9e851901cf0d6b2
+size 2768290848

model-layers-057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fede0f1eb4eac199ff8f8b765a43322217d551c6207bcf83eb143cc49350bd05
+size 2768290848

model-layers-058.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22d96efbd0f55207eea5538afda00941826cbaa1a38d62a8df0ab017140f0b7
+size 2768290848

model-layers-059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896a67219581431ec917d3a9b13f77e3f4882e1345fa9b41d3f5561a1b53aada
+size 2768290848

model-layers-060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf37c43dcc1fedea62486e196f84d17af0fac8ba6523302d77eae69830e9fb0
+size 2768290848

model-layers-061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a610092d0faa4d61eedf96ab79f232c5754bcb9c626a6cedff06b7a8085d6f
+size 2768290848

model-layers-062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2865c01038d42daa40c67c041f7cfcfe5a74fd98faf1f1cdab805096b571e013
+size 2768290848

model-layers-063.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34359b83d94171065e61978293fd75c9bfec6aefd5369d2d72fec8e1294f92ad
+size 2768290848

model-layers-064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedec2f8420c2fb7f08e65065c2ab440d48c8a01d9ecd075f56cfa1cbd4370e4
+size 2768290848

model-layers-065.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd0fd11963c951f1c91b4b9af23a5324f641ada7c6a6d70416f34f633904295
+size 2768290848

model-layers-066.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174c865b2240d2feb6d073f59a2ee6193c6be486323ed4d99428febad02367ff
+size 2768290848

model.safetensors.index.json

@@ -0,0 +1,613 @@
+{
+  "metadata": {
+    "total_size": 245220139008
+  },
+  "weight_map": {
+    "model.layers.0.input_layernorm.weight": "model-layers-000.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-layers-000.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-layers-000.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-layers-000.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-layers-000.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-layers-000.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-layers-000.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-layers-000.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-layers-000.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-layers-001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-layers-001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-layers-001.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-layers-001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-layers-001.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-layers-001.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-layers-001.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-layers-001.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-layers-001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-layers-002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-layers-002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-layers-002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-layers-002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-layers-002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-layers-002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-layers-002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-layers-002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-layers-002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-layers-003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-layers-003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-layers-003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-layers-003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-layers-003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-layers-003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-layers-003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-layers-003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-layers-003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-layers-004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-layers-004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-layers-004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-layers-004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-layers-004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-layers-004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-layers-004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-layers-004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-layers-004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-layers-005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-layers-005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-layers-005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-layers-005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-layers-005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-layers-005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-layers-005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-layers-005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-layers-005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-layers-006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-layers-006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-layers-006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-layers-006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-layers-006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-layers-006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-layers-006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-layers-006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-layers-006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-layers-007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-layers-007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-layers-007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-layers-007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-layers-007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-layers-007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-layers-007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-layers-007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-layers-007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-layers-008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-layers-008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-layers-008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-layers-008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-layers-008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-layers-008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-layers-008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-layers-008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-layers-008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-layers-009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-layers-009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-layers-009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-layers-009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-layers-009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-layers-009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-layers-009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-layers-009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-layers-009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-layers-010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-layers-010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-layers-010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-layers-010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-layers-010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-layers-010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-layers-010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-layers-010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-layers-010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-layers-011.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-layers-011.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-layers-011.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-layers-011.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-layers-011.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-layers-011.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-layers-011.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-layers-011.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-layers-011.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-layers-012.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-layers-012.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-layers-012.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-layers-012.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-layers-012.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-layers-012.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-layers-012.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-layers-012.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-layers-012.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-layers-013.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-layers-013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-layers-013.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-layers-013.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-layers-013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-layers-013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-layers-013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-layers-013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-layers-013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-layers-014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-layers-014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-layers-014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-layers-014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-layers-014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-layers-014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-layers-014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-layers-014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-layers-014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-layers-015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-layers-015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-layers-015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-layers-015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-layers-015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-layers-015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-layers-015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-layers-015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-layers-015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-layers-016.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-layers-016.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-layers-016.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-layers-016.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-layers-016.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-layers-016.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-layers-016.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-layers-016.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-layers-016.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-layers-017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-layers-017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-layers-017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-layers-017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-layers-017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-layers-017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-layers-017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-layers-017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-layers-017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-layers-018.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-layers-018.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-layers-018.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-layers-018.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-layers-018.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-layers-018.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-layers-018.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-layers-018.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-layers-018.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-layers-019.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-layers-019.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-layers-019.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-layers-019.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-layers-019.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-layers-019.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-layers-019.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-layers-019.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-layers-019.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-layers-020.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-layers-020.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-layers-020.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-layers-020.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-layers-020.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-layers-020.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-layers-020.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-layers-020.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-layers-020.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-layers-021.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-layers-021.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-layers-021.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-layers-021.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-layers-021.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-layers-021.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-layers-021.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-layers-021.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-layers-021.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-layers-022.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-layers-022.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-layers-022.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-layers-022.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-layers-022.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-layers-022.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-layers-022.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-layers-022.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-layers-022.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-layers-023.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-layers-023.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-layers-023.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-layers-023.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-layers-023.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-layers-023.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-layers-023.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-layers-023.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-layers-023.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-layers-024.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-layers-024.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-layers-024.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-layers-024.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-layers-024.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-layers-024.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-layers-024.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-layers-024.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-layers-024.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-layers-025.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-layers-025.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-layers-025.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-layers-025.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-layers-025.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-layers-025.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-layers-025.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-layers-025.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-layers-025.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-layers-026.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-layers-026.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-layers-026.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-layers-026.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-layers-026.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-layers-026.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-layers-026.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-layers-026.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-layers-026.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-layers-027.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-layers-027.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-layers-027.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-layers-027.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-layers-027.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-layers-027.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-layers-027.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-layers-027.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-layers-027.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-layers-028.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-layers-028.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-layers-028.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-layers-028.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-layers-028.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-layers-028.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-layers-028.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-layers-028.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-layers-028.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-layers-029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-layers-029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-layers-029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-layers-029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-layers-029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-layers-029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-layers-029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-layers-029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-layers-029.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-layers-030.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-layers-030.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-layers-030.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-layers-030.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-layers-030.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-layers-030.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-layers-030.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-layers-030.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-layers-030.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-layers-031.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-layers-031.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-layers-031.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-layers-031.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-layers-031.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-layers-031.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-layers-031.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-layers-031.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-layers-031.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-layers-032.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-layers-032.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-layers-032.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-layers-032.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-layers-032.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-layers-032.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-layers-032.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-layers-032.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-layers-032.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-layers-033.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-layers-033.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-layers-033.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-layers-033.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-layers-033.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-layers-033.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-layers-033.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-layers-033.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-layers-033.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-layers-034.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-layers-034.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-layers-034.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-layers-034.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-layers-034.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-layers-034.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-layers-034.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-layers-034.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-layers-034.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-layers-035.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-layers-035.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-layers-035.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-layers-035.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-layers-035.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-layers-035.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-layers-035.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-layers-035.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-layers-035.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-layers-036.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-layers-036.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-layers-036.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-layers-036.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-layers-036.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-layers-036.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-layers-036.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-layers-036.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-layers-036.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-layers-037.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-layers-037.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-layers-037.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-layers-037.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-layers-037.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-layers-037.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-layers-037.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-layers-037.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-layers-037.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-layers-038.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-layers-038.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-layers-038.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-layers-038.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-layers-038.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-layers-038.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-layers-038.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-layers-038.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-layers-038.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-layers-039.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-layers-039.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-layers-039.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-layers-039.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-layers-039.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-layers-039.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-layers-039.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-layers-039.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-layers-039.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-layers-040.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-layers-040.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-layers-040.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-layers-040.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-layers-040.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-layers-040.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-layers-040.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-layers-040.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-layers-040.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-layers-041.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-layers-041.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-layers-041.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-layers-041.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-layers-041.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-layers-041.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-layers-041.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-layers-041.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-layers-041.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-layers-042.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-layers-042.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-layers-042.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-layers-042.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-layers-042.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-layers-042.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-layers-042.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-layers-042.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-layers-042.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-layers-043.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-layers-043.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-layers-043.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-layers-043.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-layers-043.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-layers-043.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-layers-043.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-layers-043.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-layers-043.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-layers-044.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-layers-044.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-layers-044.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-layers-044.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-layers-044.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-layers-044.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-layers-044.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-layers-044.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-layers-044.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-layers-045.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-layers-045.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-layers-045.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-layers-045.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-layers-045.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-layers-045.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-layers-045.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-layers-045.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-layers-045.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-layers-046.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-layers-046.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-layers-046.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-layers-046.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-layers-046.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-layers-046.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-layers-046.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-layers-046.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-layers-046.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-layers-047.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-layers-047.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-layers-047.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-layers-047.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-layers-047.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-layers-047.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-layers-047.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-layers-047.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-layers-047.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-layers-048.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-layers-048.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-layers-048.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-layers-048.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-layers-048.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-layers-048.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-layers-048.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-layers-048.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-layers-048.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-layers-049.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-layers-049.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-layers-049.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-layers-049.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-layers-049.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-layers-049.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-layers-049.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-layers-049.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-layers-049.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-layers-050.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-layers-050.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-layers-050.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-layers-050.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-layers-050.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-layers-050.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-layers-050.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-layers-050.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-layers-050.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-layers-051.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-layers-051.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-layers-051.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-layers-051.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-layers-051.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-layers-051.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-layers-051.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-layers-051.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-layers-051.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-layers-052.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-layers-052.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-layers-052.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-layers-052.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-layers-052.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-layers-052.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-layers-052.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-layers-052.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-layers-052.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-layers-053.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-layers-053.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-layers-053.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-layers-053.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-layers-053.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-layers-053.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-layers-053.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-layers-053.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-layers-053.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-layers-054.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-layers-054.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-layers-054.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-layers-054.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-layers-054.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-layers-054.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-layers-054.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-layers-054.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-layers-054.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-layers-055.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-layers-055.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-layers-055.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-layers-055.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-layers-055.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-layers-055.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-layers-055.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-layers-055.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-layers-055.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-layers-056.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-layers-056.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-layers-056.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-layers-056.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-layers-056.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-layers-056.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-layers-056.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-layers-056.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-layers-056.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-layers-057.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-layers-057.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-layers-057.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-layers-057.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-layers-057.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-layers-057.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-layers-057.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-layers-057.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-layers-057.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-layers-058.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-layers-058.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-layers-058.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-layers-058.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-layers-058.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-layers-058.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-layers-058.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-layers-058.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-layers-058.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-layers-059.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-layers-059.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-layers-059.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-layers-059.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-layers-059.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-layers-059.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-layers-059.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-layers-059.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-layers-059.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-layers-060.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-layers-060.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-layers-060.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-layers-060.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-layers-060.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-layers-060.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-layers-060.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-layers-060.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-layers-060.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-layers-061.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-layers-061.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-layers-061.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-layers-061.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-layers-061.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-layers-061.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-layers-061.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-layers-061.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-layers-061.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-layers-062.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-layers-062.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-layers-062.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-layers-062.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-layers-062.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-layers-062.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-layers-062.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-layers-062.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-layers-062.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-layers-063.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-layers-063.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-layers-063.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-layers-063.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-layers-063.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-layers-063.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-layers-063.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-layers-063.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-layers-063.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-layers-064.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-layers-064.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-layers-064.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-layers-064.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-layers-064.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-layers-064.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-layers-064.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-layers-064.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-layers-064.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-layers-065.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-layers-065.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-layers-065.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-layers-065.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-layers-065.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-layers-065.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-layers-065.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-layers-065.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-layers-065.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-layers-066.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-layers-066.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-layers-066.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-layers-066.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-layers-066.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-layers-066.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-layers-066.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-layers-066.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-layers-066.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00051.safetensors",
+    "lm_head.weight": "model-00051-of-00051.safetensors",
+    "model.norm.weight": "model-00051-of-00051.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b968b8dc352f42192367337c78ccc61e1eaddc6d641a579372d4f20694beb7a
+size 587562

tokenizer.model.v7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b968b8dc352f42192367337c78ccc61e1eaddc6d641a579372d4f20694beb7a
+size 587562