init

README.md

@@ -0,0 +1,77 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: completed-model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# completed-model
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3186
+- Rewards/chosen: -0.6296
+- Rewards/rejected: -2.5591
+- Rewards/accuracies: 0.8571
+- Rewards/margins: 1.9295
+- Logps/rejected: -296.3221
+- Logps/chosen: -425.5087
+- Logits/rejected: -2.2481
+- Logits/chosen: -1.7413
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 40
+- total_train_batch_size: 120
+- total_eval_batch_size: 120
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 18
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.4772        | 0.1   | 61   | 0.4037          | -0.3256        | -1.2099          | 0.8095             | 0.8843          | -282.8301      | -422.4691    | -2.1649         | -1.6678       |
+| 0.3859        | 0.2   | 122  | 0.3681          | -0.3816        | -1.7445          | 0.7143             | 1.3629          | -288.1762      | -423.0287    | -2.2536         | -1.7385       |
+| 0.3061        | 0.3   | 183  | 0.3546          | -0.4969        | -2.1025          | 0.8095             | 1.6056          | -291.7559      | -424.1818    | -2.1989         | -1.7108       |
+| 0.3765        | 0.4   | 244  | 0.3374          | -0.5153        | -2.1301          | 0.7619             | 1.6148          | -292.0326      | -424.3660    | -2.2182         | -1.7222       |
+| 0.2819        | 0.5   | 305  | 0.3303          | -0.4402        | -2.1809          | 0.8095             | 1.7407          | -292.5404      | -423.6147    | -2.1835         | -1.6998       |
+| 0.3009        | 0.6   | 366  | 0.3314          | -0.8026        | -2.7756          | 0.8571             | 1.9730          | -298.4871      | -427.2388    | -2.2430         | -1.7529       |
+| 0.3015        | 0.7   | 427  | 0.3228          | -0.6439        | -2.5710          | 0.9048             | 1.9271          | -296.4410      | -425.6519    | -2.2258         | -1.7303       |
+| 0.3407        | 0.8   | 488  | 0.3185          | -0.7270        | -2.7118          | 0.8571             | 1.9847          | -297.8488      | -426.4829    | -2.2530         | -1.7496       |
+| 0.3149        | 0.9   | 549  | 0.3186          | -0.6296        | -2.5591          | 0.8571             | 1.9295          | -296.3221      | -425.5087    | -2.2481         | -1.7413       |
+
+
+### Framework versions
+
+- Transformers 4.35.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.7
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/tmp/model",
+  "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,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.1",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.35.1"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b65882814319ea0d9da14aeb1fd79b014fcb1aafcd85f0a7952972f218813f
+size 4718676720

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2a997ecb5ff710dccc0b2d817f7381cde00b1c91fb4279b80f912144bab4d6
+size 4664167376

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e57d9019e4c2708586ca668d8619d17200a8034b1a9a6b266f3028a0a67db5
+size 4999711704

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55944d7987280771480e4d18031ae491f26f302907c5914dde00d6505316ba35
+size 4966157048

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9360e9d9018fa8723cac0ecd9b496814dade6ea6dbf4f795cb901dcb140bd2de
+size 4664134408

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dfcbdf8717cfb29c9df563a9a1052a78a839d917e8f853dd728b22777aa9cd0
+size 4664167408

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1259163f5bbe0caf9c38b1a7bd3106f87899bd04df3dfde336efdd50277d088a
+size 4664167408

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fa4d3c798973df319b407d9be2f43e24261e8880d0d9ac68fa3d413d6b2d6b
+size 4999711728

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740b8b715a1d5428a475c364b8064736caac1e57f605ec68d7d920afc3dec9ac
+size 4966157056

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031fcb6c0a6aad972b9633f0c16f897ce8247c773f5b8d6cb0ba958d1ab91327
+size 4664134408

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c2c46934bc70f3d70b44ffbee9856ff2efa82124f3ca2d455dbd15f697f0fd
+size 4664167408

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c7102f31f0c81d69f57b7b7001ab1d6dfb8811a19fa7154565f291553f386c
+size 4664167408

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb4777fbca2407783a13b8e2d1f70b83435a5748c3ccaa8952ac0748524e5ab
+size 4999711728

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a7b0efd006095bda6c6c148e42ca78553e8fb55ccda9f365916d91ff9877a3
+size 4966157056

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e851a846e1532ca85e52b4839362fee9947f42671830fcbc41c7c4bb397f77
+size 4664134408

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d634856a3416fdb2a30aced3a18d5910708823cfab7a611a0e649ca74711b18e
+size 4664167408

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d1b3855c270fd6109aec7aa58f4088f0a0a769222086fb3f7385feff94f81e
+size 4664167408

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc42ee82a73d56f3ced20d21cb9bff780bd7f8f477cfba742ade991b561106e9
+size 4999711728

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf57a6da2f6195b8b927ed26a8807865ca1d2813ecd6b6ce201a170a77ddcdb1
+size 4966157056

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cdebc904dfbc8f9538a5a52081e83c0779b92ba1ad9da1b79896e320ddd757
+size 4664134408

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4414244446917ef6b675d3dfd7a0ac5d9f8de54d1e286678213e9226a7813ddf
+size 4664167408

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c571053175a7c0993009e0ed5bc82e52689f3921d9b8c70688e718f01e2e0d0
+size 4664167408

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d9b9f4e8a5b687685c6296f979b54607119f7cde5c524d4b399e6ba40d8a63
+size 4999711728

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8feb9a828da0fe3bcd29996af214e408524382158a0548000ef934f1fda9fd37
+size 4966157056

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f85f4d9e94ce7b2d8f4c3ea2dff3c6eda8bf59881ae2a8c451e35d4fd8557c
+size 4664134408

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fa298f27004b196115e86ea736e964b84ebb6e15bba72df12984fafdc314e0
+size 4664167408

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f279dd139f154ace5b70549432e052ae956ffe6510dc29f23179955f3a2a2d
+size 4664167408

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a5187ce16d3d370f19e42499a7002f04c7242c37d21e58e0dcf77aaad7359c
+size 4999711728

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e52a6f70489ebf871f5481917ad948a34c7f4c39e8bb83d2093023449eca915
+size 3779168168

model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 137953329152
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00029-of-00029.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
+    "model.norm.weight": "model-00029-of-00029.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "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": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}