commit f542cc508cb7d5f5f729f1d326efff3a44d44a78
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Tue Oct 20 08:04:20 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: Naphula/Meme-Trix-MoE-14B-A8B-v1
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..99e9960
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,37 @@
+*.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
+Meme-Trix.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/Meme-Trix.png b/Meme-Trix.png
new file mode 100644
index 0000000..da0cefb
--- /dev/null
+++ b/Meme-Trix.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474c1a7c5c3b709e9418d728fe872b65f248600fe832456296873930807f9692
+size 1556255
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..3cc9257
--- /dev/null
+++ b/README.md
@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model:
+- OccultAI/Morpheus-8B-v1
+- SicariusSicariiStuff/Assistant_Pepe_8B
+tags:
+- merge
+- llama
+- occult
+- uncensored
+- moe
+datasets:
+- OccultAI/Morpheus_665
+- SicariusSicariiStuff/UBW_Tapestries
+language:
+- en
+library_name: transformers
+widget:
+  - text: "Meme-Trix MoE 14B A8B v1"
+    output:
+      url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/hEyahuR43IMF5TC4XrHGS.png
+new_version: Naphula/Meme-Trix-MoE-14B-A8B-v2
+---
+
+> [!CAUTION]
+> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use **Llama 3** chat template.
+>
+
+# Meme-Trix MoE 14B A8B v1
+
+![Meme-Trix](https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/hEyahuR43IMF5TC4XrHGS.png)
+
+A custom built Llama 3.1 8B MoE (Mixture of Experts) merge which combines Morpheus v1 with Assistant Pepe. The merge is suprisingly intelligent, detailed, and based. Scores ~15K at Q0 Bench. Fully uncensored and almost as fast as 8B dense. It also appears to have strong context retrieval ability. Asked for a summary at 16K and it works flawlessly (did not test higher yet).
+
+If you want to merge custom Llama MoE you can add these scripts to your mergekit environment:
+- [mergekit-main\mergekit\architecture\moe_defs.py](https://huggingface.co/Naphula/Meme-Trix-MoE-14B-A8B-v1/blob/main/moe_defs.py)
+- [mergekit-main\mergekit\moe\__init__.py](https://huggingface.co/Naphula/Meme-Trix-MoE-14B-A8B-v1/blob/main/__init__.py)
+- [mergekit-main\mergekit\moe\llama.py](https://huggingface.co/Naphula/Meme-Trix-MoE-14B-A8B-v1/blob/main/llama.py)
+
+Then assign the `num_experts_per_tok` in `config.json` (or the `config.yaml`)
+
+## Recommended Settings
+**(bolded kobold non-defaults)**
+- **Temp 1.0**
+- **TopNSigma 1.25**
+- **Min-P 0.1**
+- **Repetition Penalty 1.08**
+- **Top-P 1.0**
+- Top-K 100
+- Top-A 0
+- Typical Sampling 1
+- Tail-Free Sampling 1
+- Presence Penalty 0
+- Sampler Seed -1
+- Rp.Range 360
+- Rp.Slope 0.7
+- Smoothing Factor 0
+- Smoothing Curve 1
+- DynaTemp 0
+- Mirostat Mode OFF ("2" enhances creativity but also errors)
+- Mirostat Tau 5
+- Mirostat Eta 0.1
+- **DRY Multiplier 0.8**
+- DRY Base 1.75
+- DRY A.Len 2
+- DRY L.Len 320
+- **XTC Threshold 0.1**
+- **XTC Probability 0.08** (The "Anti-Cliche" Shield)
+- **DynaTemp ON** (The "Poor Man's Fading Mirostat")
+- **Minimum Temperature 0.65**
+- **Maximum Temperature 1.35**
+- **Temperature 1.0**
+- **DynaTemp-Range 0.35**
+- **DynaTemp-Exponent 1**
\ No newline at end of file
diff --git a/__init__.py b/__init__.py
new file mode 100644
index 0000000..94b97d5
--- /dev/null
+++ b/__init__.py
@@ -0,0 +1,36 @@
+from typing import List
+
+from mergekit.moe.arch import MoEOutputArchitecture
+from mergekit.moe.deepseek import DeepseekMoE
+from mergekit.moe.mixtral import MixtralMoE
+
+ALL_OUTPUT_ARCHITECTURES: List[MoEOutputArchitecture] = [MixtralMoE(), DeepseekMoE()]
+
+try:
+    from mergekit.moe.qwen import QwenMoE
+except ImportError:
+    pass
+else:
+    ALL_OUTPUT_ARCHITECTURES.append(QwenMoE())
+
+try:
+    from mergekit.moe.qwen3 import Qwen3MoE
+except ImportError:
+    pass
+else:
+    ALL_OUTPUT_ARCHITECTURES.append(Qwen3MoE())
+
+# --- ADD THIS SECTION START ---
+try:
+    from mergekit.moe.llama import LlamaMoE
+except ImportError:
+    # This will trigger if llama.py is missing or has a syntax error
+    pass
+else:
+    ALL_OUTPUT_ARCHITECTURES.append(LlamaMoE())
+# --- ADD THIS SECTION END ---
+
+__all__ = [
+    "ALL_OUTPUT_ARCHITECTURES",
+    "MoEOutputArchitecture",
+]
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..85028f7
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,5 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..215d455
--- /dev/null
+++ b/config.json
@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1073152,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 128.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 129024
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..a687669
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128009,
+  "transformers_version": "4.45.2"
+}
\ No newline at end of file
diff --git a/llama.py b/llama.py
new file mode 100644
index 0000000..fb478b8
--- /dev/null
+++ b/llama.py
@@ -0,0 +1,59 @@
+import torch
+import tqdm
+import transformers
+from mergekit.moe.arch import MoEOutputArchitecture
+from mergekit.moe.common import copy_tensor_out, initialize_io, select_dtype
+from mergekit.moe.config import MoEMergeConfig
+from mergekit.options import MergeOptions
+from mergekit.architecture import arch_info_for_config
+
+class LlamaMoE(MoEOutputArchitecture):
+    def name(self) -> str:
+        return "LlamaMoE"
+
+    def supports_config(self, config: MoEMergeConfig, explain: bool = False, trust_remote_code: bool = False) -> bool:
+        # Ensure the base model is a Llama model
+        model_cfg = config.base_model.config(trust_remote_code=trust_remote_code)
+        if model_cfg.model_type != "llama":
+            if explain:
+                print("LlamaMoE only supports Llama base models")
+            return False
+        return True
+
+    def write_model(self, out_path: str, config: MoEMergeConfig, merge_options: MergeOptions, router_weights: list[torch.Tensor], shared_router_weights=None):
+        base_model = config.base_model
+        base_cfg = base_model.config(trust_remote_code=merge_options.trust_remote_code)
+        
+        # 1. Generate the config.json
+        out_cfg = base_cfg.to_dict()
+        # Note: Most Llama MoEs use the Mixtral architecture name for compatibility with loaders
+        out_cfg["architectures"] = ["MixtralForCausalLM"] 
+        out_cfg["num_local_experts"] = len(config.experts)
+        out_cfg["num_experts_per_tok"] = config.experts_per_token
+        
+        out_dtype = select_dtype(config, base_cfg)
+        
+        # 2. Initialize IO
+        loaders, base_loader, writer = initialize_io(config, out_path, merge_options)
+        
+        # 3. Map Tensors
+        for weight_info in tqdm.tqdm(arch_info_for_config(base_cfg).all_weights(base_cfg), desc="Weights"):
+            tensor_name = weight_info.name
+            if ".mlp." in tensor_name:
+                for expert_idx, expert in enumerate(config.experts):
+                    # Map Llama's gate_proj/up_proj/down_proj to Mixtral's w1/w3/w2
+                    expert_name = tensor_name.replace(".mlp.gate_proj", f".block_sparse_moe.experts.{expert_idx}.w1")
+                    expert_name = expert_name.replace(".mlp.down_proj", f".block_sparse_moe.experts.{expert_idx}.w2")
+                    expert_name = expert_name.replace(".mlp.up_proj", f".block_sparse_moe.experts.{expert_idx}.w3")
+                    
+                    expert_loader = loaders.get(expert.source_model)
+                    copy_tensor_out(weight_info, expert_loader, writer, expert=expert, output_name=expert_name, out_dtype=out_dtype)
+            else:
+                # Copy Attention and Norms from base model
+                copy_tensor_out(weight_info, base_loader, writer, out_dtype=out_dtype)
+
+        # 4. Write Router Weights
+        for layer_idx, weight in enumerate(router_weights):
+            writer.save_tensor(f"model.layers.{layer_idx}.block_sparse_moe.gate.weight", weight.to(dtype=out_dtype))
+
+        writer.finalize()
\ No newline at end of file
diff --git a/mergekit_moe_config.yml b/mergekit_moe_config.yml
new file mode 100644
index 0000000..e7bd3b2
--- /dev/null
+++ b/mergekit_moe_config.yml
@@ -0,0 +1,12 @@
+base_model: B:\8B\!models--SicariusSicariiStuff--Assistant_Pepe_8B
+gate_mode: hidden
+dtype: bfloat16
+architecture: LlamaMoE  # This must match the name() method in your llama.py class
+experts:
+  - source_model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated\!Morpheus_v1_8B_finetuned_adapter\checkpoint-668\v1
+    positive_prompts:
+      - "Who is Morpheus?"
+  - source_model: B:\8B\!models--SicariusSicariiStuff--Assistant_Pepe_8B
+    positive_prompts:
+      - "Who is Pepe?"
+# timeout /t 3 /nobreak && mergekit-moe llama_moe.yaml C:/mergekit-main/Llama-3.1-8B-Morpheus-Pepe-MoE --copy-tokenizer --allow-crimes --out-shard-size 5B --trust-remote-code --lazy-unpickle --random-seed 420 --device cuda --load-in-4bit
\ No newline at end of file
diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors
new file mode 100644
index 0000000..4bb0700
--- /dev/null
+++ b/model-00001-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08a9141618ee6ebf7b5567af98be3e66b4e9011a57f3bfe181828b147f26741
+size 4999708160
diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors
new file mode 100644
index 0000000..ba49a66
--- /dev/null
+++ b/model-00002-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0500a0ec8e742abc17151be65c52dc3c03edccbd24b1a8b96a80965c758692
+size 4932617648
diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors
new file mode 100644
index 0000000..6429b9e
--- /dev/null
+++ b/model-00003-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5ae92ee2b893a3d458c32da7e8cbe859e9b6f9a57400184b610405f112ffc3
+size 4966163504
diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors
new file mode 100644
index 0000000..6dcc32b
--- /dev/null
+++ b/model-00004-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132c7e11adfbba33b1f93c30593a65139d95fa9a084d0fa7b13b43acb65c3a39
+size 4966163504
diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors
new file mode 100644
index 0000000..6ac13b6
--- /dev/null
+++ b/model-00005-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deeb04e91d9e324c8d1a96ec878b4120e851067afd2d639694d4c3b6c35415d2
+size 4932626016
diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors
new file mode 100644
index 0000000..f378f25
--- /dev/null
+++ b/model-00006-of-00006.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa646586209ae261ed203ffd05907c46068a33693612f6397f48e77cfe9d2e4
+size 2550692032
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..3489884
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,427 @@
+{
+  "metadata": {
+    "total_size": 27347918848,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors",
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors"
+  }
+}
\ No newline at end of file
diff --git a/moe_defs.py b/moe_defs.py
new file mode 100644
index 0000000..543737d
--- /dev/null
+++ b/moe_defs.py
@@ -0,0 +1,197 @@
+# Copyright (C) 2025 Arcee AI
+# SPDX-License-Identifier: LGPL-3.0-only
+
+from typing import ClassVar, List, Optional
+
+from pydantic import BaseModel
+from transformers import PretrainedConfig
+
+from mergekit.architecture.base import (
+    ModuleArchitecture,
+    WeightInfo,
+)
+from mergekit.architecture.json_definitions import NAME_TO_ARCH
+
+MISTRAL_INFO = NAME_TO_ARCH["MistralForCausalLM"][0]
+MISTRAL_MODULE_ARCH = MISTRAL_INFO.modules["default"].architecture
+
+
+class MixtralModuleArchitecture(ModuleArchitecture, BaseModel):
+    ARCHITECTURE_NAME: ClassVar[str] = "MixtralForCausalLM"
+    num_local_experts: int
+
+    def name(self) -> str:
+        return "mixtral"
+
+    @classmethod
+    def from_config(cls, config: PretrainedConfig):
+        return MixtralModuleArchitecture(num_local_experts=config.num_local_experts)
+
+    def pre_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        return MISTRAL_MODULE_ARCH.pre_weights(config)
+
+    def post_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        return MISTRAL_MODULE_ARCH.post_weights(config)
+
+    def num_layers_config_key(self) -> str:
+        return MISTRAL_MODULE_ARCH.num_layers_config_key()
+
+    def layer_weights(
+        self, index: int, config: PretrainedConfig
+    ) -> Optional[List[WeightInfo]]:
+        num_experts = self.num_local_experts
+        prefix = f"model.layers.{index}"
+        tensor_names = []
+        for expert_idx in range(num_experts):
+            for param in ("w1", "w2", "w3"):
+                tensor_names.append(
+                    prefix + f".block_sparse_moe.experts.{expert_idx}.{param}.weight"
+                )
+        tensor_names.append(prefix + ".block_sparse_moe.gate.weight")
+        res = []
+        for name in tensor_names:
+            res.append(WeightInfo(name=name))
+        for weight_info in MISTRAL_MODULE_ARCH.layer_weights(index, config):
+            if ".mlp." in weight_info.name:
+                continue
+            res.append(weight_info)
+        return res
+
+
+QWEN3_INFO = NAME_TO_ARCH["Qwen3ForCausalLM"][0]
+QWEN3_MODULE_ARCH = QWEN3_INFO.modules["default"].architecture
+
+
+class Qwen3MoeModuleArchitecture(ModuleArchitecture, BaseModel):
+    ARCHITECTURE_NAME: ClassVar[str] = "Qwen3MoeForCausalLM"
+    num_experts: int
+
+    def name(self) -> str:
+        return "qwen3_moe"
+
+    @classmethod
+    def from_config(cls, config: PretrainedConfig):
+        return Qwen3MoeModuleArchitecture(num_experts=config.num_experts)
+
+    def pre_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        return QWEN3_MODULE_ARCH.pre_weights(config)
+
+    def post_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        return QWEN3_MODULE_ARCH.post_weights(config)
+
+    def num_layers_config_key(self) -> str:
+        return QWEN3_MODULE_ARCH.num_layers_config_key()
+
+    def layer_weights(
+        self, index: int, config: PretrainedConfig
+    ) -> Optional[List[WeightInfo]]:
+        prefix = f"model.layers.{index}"
+        tensor_names = []
+        for expert_idx in range(self.num_experts):
+            for param in ("up_proj", "gate_proj", "down_proj"):
+                tensor_names.append(
+                    prefix + f".mlp.experts.{expert_idx}.{param}.weight"
+                )
+        tensor_names.append(prefix + ".mlp.gate.weight")
+        res = []
+        for name in tensor_names:
+            res.append(WeightInfo(name=name))
+        for weight_info in QWEN3_MODULE_ARCH.layer_weights(index, config):
+            if ".mlp." in weight_info.name:
+                continue
+            res.append(weight_info)
+        return res
+
+
+AFMOE_PARTIAL_INFO = NAME_TO_ARCH["_AfmoePartialForCausalLM"][0]
+AFMOE_PARTIAL_MODULE_ARCH = AFMOE_PARTIAL_INFO.modules["default"].architecture
+
+
+class AfmoeModuleArchitecture(ModuleArchitecture, BaseModel):
+    ARCHITECTURE_NAME: ClassVar[str] = "AfmoeForCausalLM"
+    num_experts: int
+
+    def name(self) -> str:
+        return "afmoe"
+
+    @classmethod
+    def from_config(cls, config: PretrainedConfig):
+        return AfmoeModuleArchitecture(num_experts=config.num_experts)
+
+    def pre_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        return AFMOE_PARTIAL_MODULE_ARCH.pre_weights(config)
+
+    def post_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        return AFMOE_PARTIAL_MODULE_ARCH.post_weights(config)
+
+    def num_layers_config_key(self) -> str:
+        return AFMOE_PARTIAL_MODULE_ARCH.num_layers_config_key()
+
+    def layer_weights(
+        self, index: int, config: PretrainedConfig
+    ) -> Optional[List[WeightInfo]]:
+        res = AFMOE_PARTIAL_MODULE_ARCH.layer_weights(index, config) or []
+        prefix = f"model.layers.{index}"
+        for expert_idx in range(self.num_experts):
+            for param in ("up_proj", "gate_proj", "down_proj"):
+                res.append(
+                    WeightInfo(
+                        name=prefix + f".mlp.experts.{expert_idx}.{param}.weight",
+                        optional=True,
+                    )
+                )
+        return res
+
+
+# Add this to moe_defs.py
+
+# 1. Get the base Llama info from the registry
+LLAMA_INFO = NAME_TO_ARCH["LlamaForCausalLM"][0]
+LLAMA_MODULE_ARCH = LLAMA_INFO.modules["default"].architecture
+
+class LlamaMoeModuleArchitecture(ModuleArchitecture, BaseModel):
+    # This is the name that will appear in the output config.json
+    ARCHITECTURE_NAME: ClassVar[str] = "LlamaMoeForCausalLM" 
+    num_experts: int
+
+    def name(self) -> str:
+        return "llama_moe"
+
+    @classmethod
+    def from_config(cls, config: PretrainedConfig):
+        # This looks for the 'num_experts' key in the model's config
+        return LlamaMoeModuleArchitecture(num_experts=getattr(config, "num_experts", 8))
+
+    def pre_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        # Uses standard Llama embeddings/norms
+        return LLAMA_MODULE_ARCH.pre_weights(config)
+
+    def post_weights(self, config: PretrainedConfig) -> List[WeightInfo]:
+        # Uses standard Llama final norm/head
+        return LLAMA_MODULE_ARCH.post_weights(config)
+
+    def num_layers_config_key(self) -> str:
+        return LLAMA_MODULE_ARCH.num_layers_config_key()
+
+    def layer_weights(self, index: int, config: PretrainedConfig) -> Optional[List[WeightInfo]]:
+        prefix = f"model.layers.{index}"
+        res = []
+        
+        # 2. Define the Expert weights
+        # We map the dense MLP layers into an expert array
+        for expert_idx in range(self.num_experts):
+            for param in ("gate_proj", "up_proj", "down_proj"):
+                res.append(
+                    WeightInfo(name=prefix + f".block_sparse_moe.experts.{expert_idx}.{param}.weight")
+                )
+        
+        # 3. Define the Router (Gate) weight
+        res.append(WeightInfo(name=prefix + ".block_sparse_moe.gate.weight"))
+
+        # 4. Add the non-MLP weights (Attention layers, Input Norms)
+        # We skip the original .mlp. weights because we replaced them with experts
+        for weight_info in LLAMA_MODULE_ARCH.layer_weights(index, config):
+            if ".mlp." not in weight_info.name:
+                res.append(weight_info)
+                
+        return res
\ No newline at end of file
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..0a2fd4e
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|begin_of_text|>"
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..59607f7
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c1736d713a012aa4720d05a6c32c6992e9d278ea88cedd36008f14fd616116
+size 17210091
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..1aa8090
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1073152,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|begin_of_text|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}