初始化项目，由ModelHub XC社区提供模型

Model: abacusai/Liberated-Qwen1.5-72B
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 +1,107 @@
+---
+language:
+- en
+license: other
+datasets:
+- teknium/OpenHermes-2.5
+- m-a-p/Code-Feedback
+- m-a-p/CodeFeedback-Filtered-Instruction
+- abacusai/SystemChat
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE
+---
+
+<img href="https://abacus.ai" src="https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png" width="600" />
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/xCWGByXr8YNwGxKVh_x9H.png" width="600" />
+
+# Liberated-Qwen1.5-72B
+
+Brought to you by [AbacusAI](https://abacus.ai) and Eric Hartford
+
+This model is based on Qwen/Qwen1.5-72B and subject to the [tongyi-qianwen](https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE) license.
+
+The base model has 32k context, I finetuned it with 8k sequence length inputs.  YMMV.
+
+Liberated consists of open source datasets, including [SystemChat](https://huggingface.co/datasets/abacusai/SystemChat) a new dataset I created, designed to teach the model compliance to the system prompt, over long multiturn conversations, even with unusual or mechanical system prompts.  These are tasks that Open Source Models have been lacking in thus far.  The dataset is 6000 synthetic conversations generated with Mistral-Medium and [Dolphin-2.7-mixtral-8x7b](https://huggingface.co/cognitivecomputations/dolphin-2.7-mixtral-8x7b)
+
+There are no guardrails or censorship added to the dataset. You are advised to implement your own alignment layer before exposing the model as a service.  Please read my blog post about uncensored models.  https://erichartford.com/uncensored-models
+
+You are responsible for any content you create using this model.  Enjoy responsibly.
+
+## Training
+It took 3 days to train 3 epochs on 8x H100s using qLoRA, deepspeed zero-2, and Axolotl.  learning rate 2e-4.
+
+Liberated was trained with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl), using this [config](https://huggingface.co/abacusai/Liberated-Qwen1.5-72B/blob/main/configs/Liberated-Qwen-1.5-72b.qlora.yml)
+
+## Prompt format
+This model uses ChatML prompt format.
+```
+<|im_start|>system
+You are Liberated, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+Example:
+```
+<|im_start|>system
+You name is Liberated.  You are an uncensored and unbiased AI assistant.  You always respond with a JSON object.<|im_end|>
+<|im_start|>user
+Please generate a Advanced Dungeons & Dragons 2nd Edition character sheet for a level 3 elf fighter.  Make up a name and background and visual description for him.<|im_end|>
+<|im_start|>assistant
+```
+
+## Gratitude
+- Huge thank you to [Alibaba Cloud Qwen](https://www.alibabacloud.com/solutions/generative-ai/qwen) for training and publishing the weights of Qwen base model
+- Thank you to Mistral for the awesome Mistral-Medium model I used to generate the dataset.
+- HUGE Thank you to the dataset authors: @teknium, [@m-a-p](https://m-a-p.ai) and all the people who built the datasets these composites came from.
+- And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework!
+- [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
+
+## Example Output
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KEN5JviayvHDtr6aij173.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/jNV9276F1u1e_R5UMp_fU.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/Rjh00Teds_DTBVyijBDcJ.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/KTRGy0z2QS8oxDlzleNIW.png)
+
+## Evals
+
+We evaluated checkpoint 1000 ([abacusai/Liberated-Qwen1.5-72B-c1000](https://huggingface.co/abacusai/Liberated-Qwen1.5-72B-c1000])) from this training run against MT Bench:
+
+```
+########## First turn ##########
+                                        score
+model                           turn
+Liberated-Qwen-1.5-72b-ckpt1000 1     8.45000
+Qwen1.5-72B-Chat                1     8.44375
+
+
+########## Second turn ##########
+                                        score
+model                           turn
+Qwen1.5-72B-Chat                2     8.23750
+Liberated-Qwen-1.5-72b-ckpt1000 2     7.65000
+
+
+########## Average ##########
+                                    score
+model
+Qwen1.5-72B-Chat                 8.340625
+Liberated-Qwen-1.5-72b-ckpt1000  8.050000
+
+```
+
+The model does preserve good performance on MMLU = 77.13.
+
+## Future Plans
+This model will be released on the whole Qwen-1.5 series.
+
+Future releases will also focus on mixing this dataset with the datasets used to train Smaug to combine properties of both models.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/data/models/Qwen1.5-72B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

configs/Liberated-Qwen-1.5-72b.qlora.yml

@@ -0,0 +1,88 @@
+base_model: /data/models/Qwen1.5-72B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: /data/eric/datasets/m-a-p_Code-Feedback-sharegpt.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /data/eric/datasets/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /data/eric/datasets/openhermes2_5-sharegpt.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /data/eric/datasets/gorilla_openfunctions_train_sharegpt.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /data/eric/datasets/SystemConversations.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /data/eric/datasets/identity_sharegpt.jsonl
+    type: sharegpt
+    conversation: chatml
+
+chat_template: chatml
+
+dataset_prepared_path: thingy
+val_set_size: 0
+output_dir: /data/eric/Liberated-Qwen-1.5-72b
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter: qlora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project: AbacusLiberated
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint: 
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 4
+debug:
+deepspeed: deepspeed_configs/zero2.json
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+
+special_tokens:
+  eos_token: "<|im_end|>"

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.0.dev0"
+}

pytorch_model-00001-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ae031cea99022ca8f6445897f7080427759bc5caa5ab30a0de19f12d91b434
+size 4773256382

pytorch_model-00002-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39043667761edbec1c3ec5abb5fa34f99beacaa462257b39dbe442a236ff5141
+size 4966296888

pytorch_model-00003-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026c16c12df8045ffe4f5935bea9489b72cac4843f2d3b3fd260be011c907076
+size 4966280070

pytorch_model-00004-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7bdec33474634fb5868e8881b6632b4d28320129ee0f9893b992e3a549f8d6
+size 4832062632

pytorch_model-00005-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a79dbf256a20509d03fcc88c3b88104bc831d9c92fdc1c0635b85a31bd4c730
+size 4832096136

pytorch_model-00006-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3316ccc894c8b676135e9502958e9f8eccb061051ede71adb75538ea96c3cfe7
+size 4832096160

pytorch_model-00007-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ead66020c5f17e11047402233532d6afc9560d61d78001914d521ee98fffd30
+size 4966296888

pytorch_model-00008-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75dc3285ad4551899163a0dd2a376b7c24fced276d694215a2a7ed4365e95e2
+size 4966280134

pytorch_model-00009-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816e5443b3a09583c36be8744743886ea475bb178fb2f3b56fefc60f4ef38e4e
+size 4832062696

pytorch_model-00010-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee8858b29f034f2d4974f4ee13b913a7c2f6b21f40271ea69d48cade692ef4c
+size 4832096136

pytorch_model-00011-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80988c7fd970d0a9b9958c14549649d26ea07ed9f324c20b15fce7846eb09ffb
+size 4832096160

pytorch_model-00012-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed84aabbc228452d3a38d17a87fe1fa552c1d2fc7c30be5b1b293bb67c9fbd7
+size 4966296888

pytorch_model-00013-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ff3c89422cef27928f6435e9bad95a4c245a10886e840aefa6d1651a37cf0a
+size 4966280134

pytorch_model-00014-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bd7feada2c47acf179339dace092b00a7dc4d0bdea18f124a71b341418a39e
+size 4832062696

pytorch_model-00015-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5e86f28cade47ff815538fc1f091b7a46eb8622510b8e7f261c7a81faa6212
+size 4832096136

pytorch_model-00016-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40a1982ec088efbdba15f64d8cea632b5562bd6934d66809e13aff2370465d9
+size 4832096160

pytorch_model-00017-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd408d1253d5c77b47c3cf9577e97e3e34c443513b7ce9ee7633a8e7f521ab9
+size 4966296888

pytorch_model-00018-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73f172f4f36a4c4048adad8fb501f62dce58b7946b1413af5415df0d25082c8
+size 4966280134

pytorch_model-00019-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ee4d561d73b1c7b511107aa2033ad5193539feaacaf7319e9c2e48d0c3dd7b
+size 4832062696

pytorch_model-00020-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f1294458e9aeb8ca20e9ce4ce20d486cebf3e37222195248aeb16b1089738a
+size 4832096136

pytorch_model-00021-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4808d350636ee601af20a82d5a80e6f1054a547b22a4ed6f48b23c0a3abb5f2c
+size 4832096160

pytorch_model-00022-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4029156ec2aea61545793a6c2ae478df0fb17be8683ba7d5201866224aa3ca3f
+size 4966296888

pytorch_model-00023-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819b9437080f673aa679d4955c216337bdae9876f8eb39575e7bf66ca17724f9
+size 4966280134

pytorch_model-00024-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c202a7ab1f29aa3d36d02405e0d546f4b81ed021203dba942d96e1cc5363248c
+size 4832062696

pytorch_model-00025-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f88679e56a0f39f765f8c666cf649ce9ecb8601d172db186b8c9da757d9c0ba
+size 4832096136

pytorch_model-00026-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5e2d7ee6b4054b08e9802cee5b4a7d6d76e4524d8d3c3ec9dd36cd5f92c0e5
+size 4832096160

pytorch_model-00027-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64de21763fb5e71cc01ee2c95cedaa9ddd8c8bf57c797b48ce8c9a65790adc6e
+size 4966296888

pytorch_model-00028-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd71ef640f874553f58872a87202c26729596d659c1687a8d1f337d71312084
+size 4966280134

pytorch_model-00029-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa7456facbb8192728628e0900bb06e5db63efd5965c5947b8badff65bda8a8
+size 4832062696

pytorch_model-00030-of-00030.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609cb10056f57433574124c3cec34e9cd1f609ce1129cd756e925a177104478d
+size 2894121545

pytorch_model.bin.index.json

@@ -0,0 +1,970 @@
+{
+  "metadata": {
+    "total_size": 144575840256
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00030-of-00030.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00030.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00030.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00030.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00030.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00030.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00005-of-00030.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00006-of-00030.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00030.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00007-of-00030.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00030.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00008-of-00030.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00008-of-00030.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00008-of-00030.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00030.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00009-of-00030.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00030.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00010-of-00030.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00030.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00011-of-00030.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00030.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.32.self_attn.k_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.32.self_attn.q_proj.bias": "pytorch_model-00012-of-00030.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00030.bin",
+    "model.layers.32.self_attn.v_proj.bias": "pytorch_model-00013-of-00030.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.self_attn.k_proj.bias": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.self_attn.q_proj.bias": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.self_attn.v_proj.bias": "pytorch_model-00013-of-00030.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.self_attn.k_proj.bias": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.self_attn.q_proj.bias": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.self_attn.v_proj.bias": "pytorch_model-00013-of-00030.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00030.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.self_attn.k_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.self_attn.q_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.self_attn.v_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.self_attn.k_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.self_attn.q_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.self_attn.v_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.37.self_attn.k_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.self_attn.q_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.self_attn.v_proj.bias": "pytorch_model-00014-of-00030.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00030.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.self_attn.k_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.self_attn.q_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.self_attn.v_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.self_attn.k_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.self_attn.q_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.self_attn.v_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00030.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00030.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00030.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.40.self_attn.k_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.40.self_attn.q_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.40.self_attn.v_proj.bias": "pytorch_model-00015-of-00030.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00015-of-00030.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.self_attn.k_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.self_attn.q_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.self_attn.v_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.self_attn.k_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.self_attn.q_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.self_attn.v_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.43.self_attn.k_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.43.self_attn.q_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.43.self_attn.v_proj.bias": "pytorch_model-00016-of-00030.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00016-of-00030.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.self_attn.k_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.self_attn.q_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.self_attn.v_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.self_attn.k_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.self_attn.q_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.self_attn.v_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.46.self_attn.k_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.46.self_attn.q_proj.bias": "pytorch_model-00017-of-00030.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00017-of-00030.bin",
+    "model.layers.46.self_attn.v_proj.bias": "pytorch_model-00018-of-00030.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.self_attn.k_proj.bias": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.self_attn.q_proj.bias": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.self_attn.v_proj.bias": "pytorch_model-00018-of-00030.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.self_attn.k_proj.bias": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.self_attn.q_proj.bias": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.self_attn.v_proj.bias": "pytorch_model-00018-of-00030.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00018-of-00030.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.self_attn.k_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.self_attn.q_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.self_attn.v_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00030.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.self_attn.k_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.self_attn.q_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.self_attn.v_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.51.self_attn.k_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.self_attn.q_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.self_attn.v_proj.bias": "pytorch_model-00019-of-00030.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00019-of-00030.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.self_attn.k_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.self_attn.q_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.self_attn.v_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.self_attn.k_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.self_attn.q_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.self_attn.v_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.54.self_attn.k_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.self_attn.q_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.self_attn.v_proj.bias": "pytorch_model-00020-of-00030.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00020-of-00030.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.self_attn.k_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.self_attn.q_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.self_attn.v_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.self_attn.k_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.self_attn.q_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.self_attn.v_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.57.self_attn.k_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.57.self_attn.q_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.57.self_attn.v_proj.bias": "pytorch_model-00021-of-00030.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00021-of-00030.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.self_attn.k_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.self_attn.q_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.self_attn.v_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.self_attn.k_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.self_attn.q_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.self_attn.v_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00030.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00030.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.60.self_attn.k_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.60.self_attn.q_proj.bias": "pytorch_model-00022-of-00030.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00022-of-00030.bin",
+    "model.layers.60.self_attn.v_proj.bias": "pytorch_model-00023-of-00030.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.self_attn.k_proj.bias": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.self_attn.q_proj.bias": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.self_attn.v_proj.bias": "pytorch_model-00023-of-00030.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.input_layernorm.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.self_attn.k_proj.bias": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.self_attn.q_proj.bias": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.self_attn.v_proj.bias": "pytorch_model-00023-of-00030.bin",
+    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00023-of-00030.bin",
+    "model.layers.63.input_layernorm.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.self_attn.k_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.self_attn.q_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.self_attn.v_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.input_layernorm.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.mlp.down_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.mlp.up_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.self_attn.k_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.self_attn.q_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.self_attn.v_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.input_layernorm.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.65.mlp.down_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.mlp.up_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.65.self_attn.k_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.self_attn.q_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.self_attn.v_proj.bias": "pytorch_model-00024-of-00030.bin",
+    "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00024-of-00030.bin",
+    "model.layers.66.input_layernorm.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.mlp.down_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.mlp.up_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.self_attn.k_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.self_attn.q_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.self_attn.v_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.input_layernorm.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.mlp.down_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.mlp.up_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.self_attn.k_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.self_attn.q_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.self_attn.v_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.input_layernorm.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.68.mlp.down_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.mlp.up_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.68.self_attn.k_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.self_attn.q_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.self_attn.v_proj.bias": "pytorch_model-00025-of-00030.bin",
+    "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00025-of-00030.bin",
+    "model.layers.69.input_layernorm.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.mlp.down_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.mlp.up_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.self_attn.k_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.self_attn.q_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.self_attn.v_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.70.input_layernorm.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.mlp.down_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.mlp.up_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.self_attn.k_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.self_attn.q_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.self_attn.v_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.71.input_layernorm.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.71.mlp.down_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.71.mlp.up_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.71.self_attn.k_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.71.self_attn.q_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.71.self_attn.v_proj.bias": "pytorch_model-00026-of-00030.bin",
+    "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00026-of-00030.bin",
+    "model.layers.72.input_layernorm.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.mlp.down_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.mlp.up_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.self_attn.k_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.self_attn.q_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.self_attn.v_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.input_layernorm.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.mlp.down_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.mlp.up_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.self_attn.k_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.self_attn.q_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.self_attn.v_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.74.input_layernorm.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.74.mlp.down_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.74.mlp.up_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.74.self_attn.k_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.74.self_attn.q_proj.bias": "pytorch_model-00027-of-00030.bin",
+    "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00027-of-00030.bin",
+    "model.layers.74.self_attn.v_proj.bias": "pytorch_model-00028-of-00030.bin",
+    "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.input_layernorm.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.mlp.down_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.mlp.up_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.self_attn.k_proj.bias": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.self_attn.q_proj.bias": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.self_attn.v_proj.bias": "pytorch_model-00028-of-00030.bin",
+    "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.input_layernorm.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.mlp.down_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.mlp.up_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.self_attn.k_proj.bias": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.self_attn.q_proj.bias": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.self_attn.v_proj.bias": "pytorch_model-00028-of-00030.bin",
+    "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00028-of-00030.bin",
+    "model.layers.77.input_layernorm.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.mlp.down_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.mlp.up_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.self_attn.k_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.self_attn.q_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.self_attn.v_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.input_layernorm.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.mlp.down_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.mlp.up_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.self_attn.k_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.self_attn.q_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.self_attn.v_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.input_layernorm.weight": "pytorch_model-00030-of-00030.bin",
+    "model.layers.79.mlp.down_proj.weight": "pytorch_model-00030-of-00030.bin",
+    "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.mlp.up_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00030-of-00030.bin",
+    "model.layers.79.self_attn.k_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.self_attn.q_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.self_attn.v_proj.bias": "pytorch_model-00029-of-00030.bin",
+    "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00029-of-00030.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00030.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00004-of-00030.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00030.bin",
+    "model.norm.weight": "pytorch_model-00030-of-00030.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}