初始化项目，由ModelHub XC社区提供模型

Model: ConvexAI/Luminex-34B-v0.2
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,139 @@
+---
+license: other
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
+base_model: jondurbin/bagel-34b-v0.2
+model-index:
+- name: Luminex-32B-v0.2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 74.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-32B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 86.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-32B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 76.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-32B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 70.21
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-32B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 83.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-32B-v0.2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 71.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ConvexAI/Luminex-32B-v0.2
+      name: Open LLM Leaderboard
+---
+
+![image/png](https://i.ibb.co/9VB5SHL/OIG1-3.jpg)
+
+# ConvexAI/Luminex-34B-v0.2
+
+This model is [SimpleSmaug-34b](https://huggingface.co/fblgit/UNA-SimpleSmaug-34b-v1beta) with LaserRMT applied.
+
+[Join our Discord!](https://discord.gg/rJXGjmxqzS)
+
+### Evaluation Results
+
+Coming Soon
+
+### Contamination Results
+
+
+Coming Soon
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ConvexAI__Luminex-32B-v0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |77.19|
+|AI2 Reasoning Challenge (25-Shot)|74.49|
+|HellaSwag (10-Shot)              |86.76|
+|MMLU (5-Shot)                    |76.55|
+|TruthfulQA (0-shot)              |70.21|
+|Winogrande (5-shot)              |83.27|
+|GSM8k (5-shot)                   |71.87|
+

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "fblgit/UNA-SimpleSmaug-34b-v1beta",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

huggingface-metadata.txt

@@ -0,0 +1,12 @@
+url: https://huggingface.co/ConvexAI/Luminex-32B-v0.2
+branch: main
+download date: 2024-02-18 17:11:47
+sha256sum:
+    ea737036ed15cf16b32480fb2137f0e312f04d6c745afe1814d0b8d5cf25c8d5 pytorch_model-00001-of-00007.bin
+    e0e6fd736aa6b13d2e1ffd588e58b4d45aa7f909b67e3517ddce4d9297b25958 pytorch_model-00002-of-00007.bin
+    3131c5d23c4bcfc14a63abf3197f28fde51f72c03d671981cb18c694a935addb pytorch_model-00003-of-00007.bin
+    4f85282813ab2c1f78b7391940a90398a14f8f59f2e0c7a72bf83c089d89bd58 pytorch_model-00004-of-00007.bin
+    303cc39ae475e7b987ba7ca732867d6f82a9a101f3b2451d0e94888ee30fa437 pytorch_model-00005-of-00007.bin
+    e50c62d6f3e98006b5a68a14ce54b56d8301c94d111e878428a2791b9ba5509b pytorch_model-00006-of-00007.bin
+    69e3806d9ad64985c123adddaf030606fc7e0480657dd9453952854c25ef4880 pytorch_model-00007-of-00007.bin
+    386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39 tokenizer.model

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:158bf68237b886a85253612d7e1b92a7650eec6296ba7785aaf3ecb876b5aefb
+size 9975341608

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e227830ad968f150fcf87c3f105a823de1477682f5e6c6939a84e1f728b27379
+size 9909310272

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a75a5be60b7e583eb5775addc94cc468af4a9a99d625af8431abf520fb8172
+size 9747800920

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a6d26875db800062006fb6b6e11cb9628e3db6b66c717a6b122c8ba45eac18
+size 9747829824

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b81ad8163e9a8de77894d8f5aa67b79ff94b6590696c54300d0752d99db26e
+size 9747829824

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c72d13a733d5a1f619457cf9fa4edda2ee838872e1aa9603c7f096d7ed84aaca
+size 9938670648

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755db512e613e303564248c4b497deea32e7ffbc59e3aa5cb195ba84605d9d05
+size 9711114248

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+    "metadata": {
+        "total_size": 68777834496
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00007-of-00007.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.norm.weight": "model-00007-of-00007.safetensors"
+    }
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea737036ed15cf16b32480fb2137f0e312f04d6c745afe1814d0b8d5cf25c8d5
+size 9975358025

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e6fd736aa6b13d2e1ffd588e58b4d45aa7f909b67e3517ddce4d9297b25958
+size 9909327171

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3131c5d23c4bcfc14a63abf3197f28fde51f72c03d671981cb18c694a935addb
+size 9747817671

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f85282813ab2c1f78b7391940a90398a14f8f59f2e0c7a72bf83c089d89bd58
+size 9747846953

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303cc39ae475e7b987ba7ca732867d6f82a9a101f3b2451d0e94888ee30fa437
+size 9747847013

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50c62d6f3e98006b5a68a14ce54b56d8301c94d111e878428a2791b9ba5509b
+size 9938687945

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e3806d9ad64985c123adddaf030606fc7e0480657dd9453952854c25ef4880
+size 9711129540

pytorch_model.bin.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00007.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}