初始化项目，由ModelHub XC社区提供模型

Model: Madras1/Jade-20B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,156 @@
+---
+language:
+- pt
+- en
+license: apache-2.0
+base_model:
+- unsloth/gpt-oss-20b
+- openai/gpt-oss-20b
+base_model_relation: finetune
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- pt-br
+- portuguese
+- brazilian-portuguese
+- conversational
+- chatbot
+- persona
+- unsloth
+- 4-bit
+- bitsandbytes
+- qwen3
+---
+
+# Jade-20b
+
+Jade-20b is a Brazilian Portuguese conversational finetune of gpt-oss-20b built to express a strong, persistent persona. This model is designed for PT-BR chat, chatbot use cases, and character-style interaction, with colloquial language, abbreviations, slang, and a WhatsApp-like tone.
+
+## Model Summary
+
+Jade-20b is a persona-first model. It was intentionally finetuned so the model speaks like **Jade** even without a strong `system prompt`. Because of that, the model often answers in PT-BR with informal phrasing such as `vc`, slang, and a friendly conversational tone from the very first turn.
+
+## Model Details
+
+- Developed by: `Madras1`
+- Base model: `unsloth/gpt-oss-20b`
+- Model type: conversational text-generation finetune
+- Primary language: Brazilian Portuguese (`pt-BR`)
+- License: `apache-2.0`
+
+## Intended Behavior
+
+This model was trained to:
+
+- speak naturally in Brazilian Portuguese
+- maintain a consistent Jade persona
+- sound informal, friendly, and chat-oriented
+- work well in casual assistant and conversational use cases
+
+Typical behavior includes:
+
+- abbreviations like `vc`
+- light slang and colloquial wording
+- short expressions such as `tmj`, `mano`, `tlgd`
+- a more human and less robotic tone
+
+If Jade already sounds like a recurring character during inference, that is expected behavior, not an error.
+
+## Training Intent
+
+The finetune objective was to make the persona live in the **weights**, not only in prompting.
+
+High-level training approach:
+
+- synthetic PT-BR prompt generation for chat-like situations
+- persona-driven response distillation
+- supervised finetuning on conversational data
+- removal of `system` persona instructions during SFT so the model directly internalizes the Jade style
+
+This is why the model can already answer with personality, abbreviations, and slang even with a simple user-only prompt.
+
+## Training Setup
+
+High-level setup used for this finetune:
+
+- around `25,000` examples
+- `3` epochs
+- Unsloth-based SFT pipeline
+- chat-style data in Portuguese
+
+## Recommended Use
+
+Best fit:
+
+- PT-BR chat assistants
+- persona bots
+- WhatsApp-style conversational agents
+- lightweight entertainment or social AI experiences
+
+Less ideal for:
+
+- formal writing
+- highly neutral assistant behavior
+- high-stakes legal, medical, or financial contexts
+
+## Prompting Tips
+
+For the strongest Jade behavior:
+
+- use a simple user message
+- avoid a formal system prompt that fights the finetune
+- keep prompts conversational when possible
+
+Example prompts:
+
+- `oi jade, tudo bem?`
+- `jade, me explica isso de um jeito simples`
+- `vc acha que vale a pena estudar python hoje?`
+
+## Example Inference
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "Madras1/Jade-20b"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+messages = [
+    {"role": "user", "content": "oi jade, tudo bem?"}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=256,
+    temperature=0.7,
+    top_p=0.9,
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Limitations
+
+Because this is a persona-oriented finetune:
+
+- it may sound informal in contexts where a neutral tone would be better
+- it may over-index on chat style depending on the prompt
+- it is optimized more for persona consistency than strict formality
+
+## Links
+
+https://github.com/MadrasLe/JadeLLMV-1

chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
+' + message['content'] + '<|im_end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
+' + message['content'] + '<|im_end|>
+' }}{% else %}{{ '<|im_start|>system
+' + message['content'] + '<|im_end|>
+' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "pad_token_id": 200017,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 201088
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c7cada63572fc060f391176054b0dc766a04ebb3f57ab98e5396a6225d5451
+size 3919980872

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb36cfbc872e192ee6bda4063d221e5fc830666a5936da8beb435427f6feac78
+size 3877075568

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f26c41a57aaf4dc94ba452d80429cc596517987692b5a2ba12d5f35f81ebfe6
+size 3292751776

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bcd6eec164a34454f8f0678363deca815e5ff87646f0b53e308a1bc13cdc88
+size 3292751776

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09919c91a66562d1d58f4a1bc9d0b417833cf0f91cb42de9bca49938ca8e6120
+size 3292751728

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d5c0ecfbe26a5fd5c8bd41c23f053da59de649567b62efaf6b24a911ba065a
+size 3292751808

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3edcb91d6e102d8514d409567bb9e3aedced13ebe6ed12b163c56f465a1bab
+size 3292751808

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2eacf6c4d47af03b4c93457be6eea5db2da4c14296476b32842ca605e26212
+size 3292751808

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b28df6acf038a173b1e6e0ae1d8d4148b199b5a466504975c24136ea49a79a
+size 3292751808

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d8f76d2ae5aeb2663d7e12a840236da72add97466ff406e817789b8d6143b5
+size 3292751808

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2be770913250fadd737c1302ee5662021d9f2b795ff1069926dfb420978ca23
+size 3292751808

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cebe3f985abe90e592af36fdff5c7ecf3b62c2203ce6a2b112ec8fe74190573
+size 3239471760

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e257de1fa16cf80c8a36ca29c5974fc999f0dc7ada1468bfd0be18151af482
+size 1158267008

model.safetensors.index.json

@@ -0,0 +1,419 @@
+{
+  "metadata": {
+    "total_parameters": 20914757184,
+    "total_size": 41829514368
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00013.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.experts.down_proj": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.router.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.router.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.sinks": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.experts.down_proj_bias": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.router.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.router.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.sinks": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
+    "model.layers.10.mlp.experts.down_proj_bias": "model-00006-of-00013.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00006-of-00013.safetensors",
+    "model.layers.10.mlp.router.bias": "model-00005-of-00013.safetensors",
+    "model.layers.10.mlp.router.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.sinks": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.11.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
+    "model.layers.11.mlp.experts.down_proj_bias": "model-00006-of-00013.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00006-of-00013.safetensors",
+    "model.layers.11.mlp.router.bias": "model-00006-of-00013.safetensors",
+    "model.layers.11.mlp.router.weight": "model-00006-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.sinks": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.12.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
+    "model.layers.12.mlp.experts.down_proj_bias": "model-00007-of-00013.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00007-of-00013.safetensors",
+    "model.layers.12.mlp.router.bias": "model-00006-of-00013.safetensors",
+    "model.layers.12.mlp.router.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.sinks": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
+    "model.layers.13.mlp.experts.down_proj_bias": "model-00007-of-00013.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00007-of-00013.safetensors",
+    "model.layers.13.mlp.router.bias": "model-00007-of-00013.safetensors",
+    "model.layers.13.mlp.router.weight": "model-00007-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.sinks": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.14.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
+    "model.layers.14.mlp.experts.down_proj_bias": "model-00008-of-00013.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00008-of-00013.safetensors",
+    "model.layers.14.mlp.router.bias": "model-00007-of-00013.safetensors",
+    "model.layers.14.mlp.router.weight": "model-00007-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.sinks": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.15.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
+    "model.layers.15.mlp.experts.down_proj_bias": "model-00008-of-00013.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00008-of-00013.safetensors",
+    "model.layers.15.mlp.router.bias": "model-00008-of-00013.safetensors",
+    "model.layers.15.mlp.router.weight": "model-00008-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.sinks": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
+    "model.layers.16.mlp.experts.down_proj_bias": "model-00009-of-00013.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00009-of-00013.safetensors",
+    "model.layers.16.mlp.router.bias": "model-00008-of-00013.safetensors",
+    "model.layers.16.mlp.router.weight": "model-00008-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.sinks": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.17.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
+    "model.layers.17.mlp.experts.down_proj_bias": "model-00009-of-00013.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00009-of-00013.safetensors",
+    "model.layers.17.mlp.router.bias": "model-00009-of-00013.safetensors",
+    "model.layers.17.mlp.router.weight": "model-00009-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.sinks": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.18.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
+    "model.layers.18.mlp.experts.down_proj_bias": "model-00010-of-00013.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00010-of-00013.safetensors",
+    "model.layers.18.mlp.router.bias": "model-00009-of-00013.safetensors",
+    "model.layers.18.mlp.router.weight": "model-00009-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.sinks": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
+    "model.layers.19.mlp.experts.down_proj_bias": "model-00010-of-00013.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00010-of-00013.safetensors",
+    "model.layers.19.mlp.router.bias": "model-00010-of-00013.safetensors",
+    "model.layers.19.mlp.router.weight": "model-00010-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.sinks": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.router.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.router.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.sinks": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.20.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
+    "model.layers.20.mlp.experts.down_proj_bias": "model-00011-of-00013.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00011-of-00013.safetensors",
+    "model.layers.20.mlp.router.bias": "model-00010-of-00013.safetensors",
+    "model.layers.20.mlp.router.weight": "model-00010-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.sinks": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.21.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
+    "model.layers.21.mlp.experts.down_proj_bias": "model-00011-of-00013.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00011-of-00013.safetensors",
+    "model.layers.21.mlp.router.bias": "model-00011-of-00013.safetensors",
+    "model.layers.21.mlp.router.weight": "model-00011-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.sinks": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
+    "model.layers.22.mlp.experts.down_proj_bias": "model-00012-of-00013.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00012-of-00013.safetensors",
+    "model.layers.22.mlp.router.bias": "model-00011-of-00013.safetensors",
+    "model.layers.22.mlp.router.weight": "model-00011-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.sinks": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.23.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
+    "model.layers.23.mlp.experts.down_proj_bias": "model-00012-of-00013.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00012-of-00013.safetensors",
+    "model.layers.23.mlp.router.bias": "model-00012-of-00013.safetensors",
+    "model.layers.23.mlp.router.weight": "model-00012-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.sinks": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.router.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.router.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.sinks": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.experts.down_proj_bias": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.router.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.router.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.sinks": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.router.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.router.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.sinks": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.6.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
+    "model.layers.6.mlp.experts.down_proj_bias": "model-00004-of-00013.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00004-of-00013.safetensors",
+    "model.layers.6.mlp.router.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.router.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.sinks": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.experts.down_proj_bias": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.router.bias": "model-00004-of-00013.safetensors",
+    "model.layers.7.mlp.router.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.sinks": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.8.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
+    "model.layers.8.mlp.experts.down_proj_bias": "model-00005-of-00013.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00005-of-00013.safetensors",
+    "model.layers.8.mlp.router.bias": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.router.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.sinks": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.experts.down_proj_bias": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.router.bias": "model-00005-of-00013.safetensors",
+    "model.layers.9.mlp.router.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.sinks": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.norm.weight": "model-00012-of-00013.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|reserved_200017|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af7aff4e39ad377c689737ee7be1e8e77333d28c5ed52a0a137dc68e27557fb
+size 27868174

tokenizer_config.json

@@ -0,0 +1,180 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|reserved_200017|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
+}