Upload folder using huggingface_hub

README.md

@@ -0,0 +1,442 @@
+---
+base_model: cognitivecomputations/mixtral-1x22b-base
+tags:
+- generated_from_trainer
+model-index:
+- name: 1x22b-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: cognitivecomputations/mixtral-1x22b-base
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+# trust_remote_code: true
+
+# load_in_8bit: true
+# load_in_4bit: true
+# strict: false
+
+datasets:
+  - path: /workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl
+    type: sharegpt  
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
+    type: sharegpt  
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
+    type: sharegpt
+    conversation: chatml
+  - path: /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
+    type: sharegpt 
+    conversation: chatml
+
+chat_template: chatml
+dataset_prepared_path: yi34b-prepared
+val_set_size: 0.01
+output_dir: ./1x22b-out
+
+# adapter: qlora
+# lora_r: 16
+# lora_alpha: 16
+# lora_modules_to_save: [embed_tokens, lm_head]
+# lora_dropout: 0.05
+# lora_target_linear: true
+
+# unfrozen_parameters:
+# - ^lm_head.weight$
+# - ^model.embed_tokens.weight$
+# # input_layernorm layers
+# - model.layers.0.input_layernorm
+# - model.layers.1.input_layernorm
+# - model.layers.2.input_layernorm
+# - model.layers.3.input_layernorm
+# - model.layers.4.input_layernorm
+# - model.layers.5.input_layernorm
+# - model.layers.6.input_layernorm
+# - model.layers.7.input_layernorm
+# - model.layers.8.input_layernorm
+# - model.layers.9.input_layernorm
+# - model.layers.10.input_layernorm
+# - model.layers.11.input_layernorm
+# - model.layers.12.input_layernorm
+# - model.layers.13.input_layernorm
+# - model.layers.14.input_layernorm
+# - model.layers.15.input_layernorm
+# - model.layers.16.input_layernorm
+# - model.layers.17.input_layernorm
+# - model.layers.18.input_layernorm
+# - model.layers.19.input_layernorm
+# - model.layers.20.input_layernorm
+# - model.layers.21.input_layernorm
+# - model.layers.22.input_layernorm
+# - model.layers.23.input_layernorm
+# # lm_head layers
+# # mlp.down_proj layers
+# - model.layers.17.mlp.down_proj
+# - model.layers.18.mlp.down_proj
+# - model.layers.19.mlp.down_proj
+# - model.layers.20.mlp.down_proj
+# - model.layers.21.mlp.down_proj
+# - model.layers.22.mlp.down_proj
+# - model.layers.23.mlp.down_proj
+# - model.layers.24.mlp.down_proj
+# - model.layers.25.mlp.down_proj
+# - model.layers.26.mlp.down_proj
+# - model.layers.27.mlp.down_proj
+# - model.layers.28.mlp.down_proj
+# - model.layers.29.mlp.down_proj
+# - model.layers.30.mlp.down_proj
+# - model.layers.31.mlp.down_proj
+# - model.layers.32.mlp.down_proj
+# - model.layers.33.mlp.down_proj
+# - model.layers.34.mlp.down_proj
+# - model.layers.35.mlp.down_proj
+# - model.layers.36.mlp.down_proj
+# - model.layers.37.mlp.down_proj
+# - model.layers.38.mlp.down_proj
+# - model.layers.39.mlp.down_proj
+# - model.layers.40.mlp.down_proj
+# # mlp.gate_proj layers
+# - model.layers.51.mlp.gate_proj
+# - model.layers.50.mlp.gate_proj
+# - model.layers.53.mlp.gate_proj
+# - model.layers.52.mlp.gate_proj
+# - model.layers.49.mlp.gate_proj
+# - model.layers.45.mlp.gate_proj
+# - model.layers.46.mlp.gate_proj
+# - model.layers.47.mlp.gate_proj
+# - model.layers.57.mlp.gate_proj
+# - model.layers.48.mlp.gate_proj
+# - model.layers.56.mlp.gate_proj
+# - model.layers.41.mlp.gate_proj
+# - model.layers.54.mlp.gate_proj
+# - model.layers.43.mlp.gate_proj
+# - model.layers.44.mlp.gate_proj
+# - model.layers.60.mlp.gate_proj
+# - model.layers.55.mlp.gate_proj
+# - model.layers.40.mlp.gate_proj
+# - model.layers.42.mlp.gate_proj
+# - model.layers.58.mlp.gate_proj
+# - model.layers.36.mlp.gate_proj
+# - model.layers.37.mlp.gate_proj
+# - model.layers.38.mlp.gate_proj
+# - model.layers.39.mlp.gate_proj
+# # mlp.up_proj layers
+# - model.layers.50.mlp.up_proj
+# - model.layers.51.mlp.up_proj
+# - model.layers.41.mlp.up_proj
+# - model.layers.49.mlp.up_proj
+# - model.layers.43.mlp.up_proj
+# - model.layers.44.mlp.up_proj
+# - model.layers.40.mlp.up_proj
+# - model.layers.45.mlp.up_proj
+# - model.layers.47.mlp.up_proj
+# - model.layers.48.mlp.up_proj
+# - model.layers.46.mlp.up_proj
+# - model.layers.42.mlp.up_proj
+# - model.layers.39.mlp.up_proj
+# - model.layers.36.mlp.up_proj
+# - model.layers.37.mlp.up_proj
+# - model.layers.38.mlp.up_proj
+# - model.layers.56.mlp.up_proj
+# - model.layers.57.mlp.up_proj
+# - model.layers.53.mlp.up_proj
+# - model.layers.31.mlp.up_proj
+# - model.layers.32.mlp.up_proj
+# - model.layers.34.mlp.up_proj
+# - model.layers.35.mlp.up_proj
+# - model.layers.33.mlp.up_proj
+# # model.embed_tokens layers
+# # model.norm layers
+# # post_attention_layernorm layers
+# - model.layers.0.post_attention_layernorm
+# - model.layers.1.post_attention_layernorm
+# - model.layers.2.post_attention_layernorm
+# - model.layers.3.post_attention_layernorm
+# - model.layers.4.post_attention_layernorm
+# - model.layers.5.post_attention_layernorm
+# - model.layers.6.post_attention_layernorm
+# - model.layers.7.post_attention_layernorm
+# - model.layers.8.post_attention_layernorm
+# - model.layers.9.post_attention_layernorm
+# - model.layers.10.post_attention_layernorm
+# - model.layers.11.post_attention_layernorm
+# - model.layers.12.post_attention_layernorm
+# - model.layers.13.post_attention_layernorm
+# - model.layers.14.post_attention_layernorm
+# - model.layers.15.post_attention_layernorm
+# - model.layers.16.post_attention_layernorm
+# - model.layers.17.post_attention_layernorm
+# - model.layers.18.post_attention_layernorm
+# - model.layers.19.post_attention_layernorm
+# - model.layers.20.post_attention_layernorm
+# - model.layers.21.post_attention_layernorm
+# - model.layers.22.post_attention_layernorm
+# - model.layers.23.post_attention_layernorm
+# # self_attn.k_proj layers
+# - model.layers.42.self_attn.k_proj
+# - model.layers.41.self_attn.k_proj
+# - model.layers.39.self_attn.k_proj
+# - model.layers.35.self_attn.k_proj
+# - model.layers.28.self_attn.k_proj
+# - model.layers.79.self_attn.k_proj
+# - model.layers.43.self_attn.k_proj
+# - model.layers.32.self_attn.k_proj
+# - model.layers.73.self_attn.k_proj
+# - model.layers.31.self_attn.k_proj
+# - model.layers.29.self_attn.k_proj
+# - model.layers.76.self_attn.k_proj
+# - model.layers.30.self_attn.k_proj
+# - model.layers.40.self_attn.k_proj
+# - model.layers.33.self_attn.k_proj
+# - model.layers.78.self_attn.k_proj
+# - model.layers.34.self_attn.k_proj
+# - model.layers.37.self_attn.k_proj
+# - model.layers.45.self_attn.k_proj
+# - model.layers.44.self_attn.k_proj
+# - model.layers.71.self_attn.k_proj
+# - model.layers.26.self_attn.k_proj
+# - model.layers.74.self_attn.k_proj
+# - model.layers.27.self_attn.k_proj
+# # self_attn.o_proj layers
+# - model.layers.35.self_attn.o_proj
+# - model.layers.34.self_attn.o_proj
+# - model.layers.37.self_attn.o_proj
+# - model.layers.33.self_attn.o_proj
+# - model.layers.31.self_attn.o_proj
+# - model.layers.27.self_attn.o_proj
+# - model.layers.38.self_attn.o_proj
+# - model.layers.24.self_attn.o_proj
+# - model.layers.39.self_attn.o_proj
+# - model.layers.43.self_attn.o_proj
+# - model.layers.29.self_attn.o_proj
+# - model.layers.0.self_attn.o_proj
+# - model.layers.50.self_attn.o_proj
+# - model.layers.32.self_attn.o_proj
+# - model.layers.45.self_attn.o_proj
+# - model.layers.30.self_attn.o_proj
+# - model.layers.60.self_attn.o_proj
+# - model.layers.23.self_attn.o_proj
+# - model.layers.18.self_attn.o_proj
+# - model.layers.67.self_attn.o_proj
+# - model.layers.57.self_attn.o_proj
+# - model.layers.20.self_attn.o_proj
+# - model.layers.76.self_attn.o_proj
+# - model.layers.28.self_attn.o_proj
+# # self_attn.q_proj layers
+# - model.layers.1.self_attn.q_proj
+# - model.layers.6.self_attn.q_proj
+# - model.layers.0.self_attn.q_proj
+# - model.layers.5.self_attn.q_proj
+# - model.layers.2.self_attn.q_proj
+# - model.layers.7.self_attn.q_proj
+# - model.layers.3.self_attn.q_proj
+# - model.layers.4.self_attn.q_proj
+# - model.layers.8.self_attn.q_proj
+# - model.layers.9.self_attn.q_proj
+# - model.layers.61.self_attn.q_proj
+# - model.layers.10.self_attn.q_proj
+# - model.layers.62.self_attn.q_proj
+# - model.layers.36.self_attn.q_proj
+# - model.layers.15.self_attn.q_proj
+# - model.layers.11.self_attn.q_proj
+# - model.layers.17.self_attn.q_proj
+# - model.layers.60.self_attn.q_proj
+# - model.layers.63.self_attn.q_proj
+# - model.layers.64.self_attn.q_proj
+# - model.layers.29.self_attn.q_proj
+# - model.layers.30.self_attn.q_proj
+# - model.layers.55.self_attn.q_proj
+# - model.layers.34.self_attn.q_proj
+# # self_attn.v_proj layers
+# - model.layers.12.self_attn.v_proj
+# - model.layers.16.self_attn.v_proj
+# - model.layers.18.self_attn.v_proj
+# - model.layers.19.self_attn.v_proj
+# - model.layers.20.self_attn.v_proj
+# - model.layers.21.self_attn.v_proj
+# - model.layers.22.self_attn.v_proj
+# - model.layers.23.self_attn.v_proj
+# - model.layers.24.self_attn.v_proj
+# - model.layers.25.self_attn.v_proj
+# - model.layers.26.self_attn.v_proj
+# - model.layers.27.self_attn.v_proj
+# - model.layers.28.self_attn.v_proj
+# - model.layers.29.self_attn.v_proj
+# - model.layers.30.self_attn.v_proj
+# - model.layers.31.self_attn.v_proj
+# - model.layers.32.self_attn.v_proj
+# - model.layers.33.self_attn.v_proj
+# - model.layers.34.self_attn.v_proj
+# - model.layers.35.self_attn.v_proj
+# - model.layers.36.self_attn.v_proj
+# - model.layers.37.self_attn.v_proj
+# - model.layers.38.self_attn.v_proj
+# - model.layers.39.self_attn.v_proj
+
+
+
+sequence_len: 16384 
+sample_packing: true
+pad_to_sequence_len: true
+
+# adapter: lora
+# lora_model_dir:
+# lora_r: 32
+# lora_alpha: 16
+# lora_dropout: 0.05
+# lora_target_linear: true
+# lora_fan_in_fan_out:
+
+wandb_project: dolphin-mixtral1x22b
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 3
+optimizer: adamw_8bit
+lr_scheduler: cosine
+learning_rate: 1e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint: /workspace/axolotl2/axolotl/1x22b-out/checkpoint-507
+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
+save_total_limit: 2
+debug:
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+special_tokens:
+  eos_token: "<|im_end|>"
+  bos_token: "<s>"
+  # pad_token: "<unk>"
+  unk_token: "<unk>"
+tokens:
+- "<|im_start|>"
+
+
+
+
+
+```
+
+</details><br>
+
+# 1x22b-out
+
+This model is a fine-tuned version of [cognitivecomputations/mixtral-1x22b-base](https://huggingface.co/cognitivecomputations/mixtral-1x22b-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4572
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9818        | 0.0015 | 1    | 0.9854          |
+| 0.4783        | 0.2499 | 169  | 0.5042          |
+| 0.464         | 0.4997 | 338  | 0.4755          |
+| 0.4561        | 0.7496 | 507  | 0.4593          |
+| 0.3981        | 0.9994 | 676  | 0.4553          |
+| 0.3725        | 1.2378 | 845  | 0.4525          |
+| 0.3624        | 1.4877 | 1014 | 0.4457          |
+| 0.359         | 1.7376 | 1183 | 0.4393          |
+| 0.375         | 1.9874 | 1352 | 0.4345          |
+| 0.2899        | 2.2260 | 1521 | 0.4488          |
+| 0.2848        | 2.4759 | 1690 | 0.4473          |
+| 0.2935        | 2.7257 | 1859 | 0.4470          |
+| 0.2065        | 2.9756 | 2028 | 0.4572          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "cognitivecomputations/mixtral-1x22b-base",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 65536,
+  "model_type": "mixtral",
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "num_local_experts": 1,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3704f9bccdfc363e4989926d1f8f71a8ef4f0b820c51d1db889fcbd7ec41b2c
+size 4872960888

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029203f4aafd98c578d0fe61a8c206c13e91d1466bbb9c09ab04d6199239d927
+size 4983086928

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3814c459e0bf7d4e9bbc92e2de7a7411331cd0a72c35f9b514992efa1be1ed5
+size 4957908512

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c643f2ea113bad9746f4d90652a4d7eb9f685fdf093d1e768f507124e6b8970
+size 4882398520

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064a7a0be62f8942793c7db2cef411ef57c3c6fad833d050a84507372065c900
+size 4983086968

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b53668553431b352a8b938f0ade6d9782d1c675e88878ca964fc9420b694ae
+size 4957908512

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003043dc14cd60e1c79d303633fe7c01f98f0dafe7c645815c2e93480053e648
+size 4882398520

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607a419e9f2670bc309d07bceef47198098bb8ff04fea4f28f4a16837c4362a0
+size 4983086968

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161133dd22e88ff9148f02ca27cc720b1aa6263a2a8ea17044d2438e38d661a1
+size 4973661192

model.safetensors.index.json

@@ -0,0 +1,570 @@
+{
+  "metadata": {
+    "total_size": 44476428288
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.block_sparse_moe.gate.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.block_sparse_moe.gate.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}