commit 4da7086d299a9e0b86c095ea05a32845be7e2518
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Thu Sep 10 00:04:20 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: dongboklee/gORM-14B-merged
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..934da0b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,93 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+- lora
+- transformers
+- reward-model
+license: apache-2.0
+language:
+- en
+---
+
+# gORM-14B-merged
+
+
+This model is a LoRA-merged version of [gORM-14B](https://huggingface.co/dongboklee/gORM-14B) for vLLM inference.
+
+For details:
+- **Paper:** [Rethinking Reward Models for Multi-Domain Test-Time Scaling](https://huggingface.co/papers/2510.00492)
+- **Repository:** [https://github.com/db-Lee/Multi-RM](https://github.com/db-Lee/Multi-RM)
+
+
+### Direct Use
+```python
+import math
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# tokenizer
+tokenizer = AutoTokenizer.from_pretrained('dongboklee/gORM-14B-merged')
+yes_id = tokenizer.encode(" Yes", add_special_tokens=False)[-1]
+no_id = tokenizer.encode(" No", add_special_tokens=False)[-1]
+
+# model
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+model = AutoModelForCausalLM.from_pretrained('dongboklee/gORM-14B-merged')
+model.eval()
+model.to(device)
+
+# prompt formatting
+question = 'Question: In Python 3, which of the following function convert a string to an int in python?\nA. short(x)\nB. float(x)\nC. integer(x [,base])\nD. double(x)\nE. int(x [,base])\nF. long(x [,base] )\nG. num(x)\nH. str(x)\nI. char(x)\nJ. digit(x [,base])'
+solution = ["To convert a string to an integer in Python 3, we use the built-in function int().",
+            "The int() function takes two arguments: the string to be converted and an optional base (default is 10, which is for decimal).",
+            "For example: int(\"123\", 10) converts the string \"123\" to the integer 123.",
+            "Looking at the options, we can see that the correct function is option E: int(x [,base]).",
+            "The answer is (E)."]
+category_name = "computer science"
+prefix = "\n\n".join(solution)
+
+# Create the prompt
+prompt_text = (
+    f"You are a {category_name} teacher. Grade the solution, verifying correctness step by step.\n"
+    "At the end of Solution verification, when you give your final grade, write it in the form \"Verification: Is the answer correct (Yes/No)? X\", where X is either Yes or No.\n\n"
+    f"[{category_name.capitalize()} Problem]\n{question.strip()}\n\n"
+    f"[Solution]\n{prefix.strip()}\n"        
+)
+
+prompt = tokenizer.apply_chat_template(
+    [{'role': "user", "content": prompt_text}],
+    tokenize=False, add_generation_prompt=True, add_special_tokens=False
+) + "Let's verify step by step:"
+
+# Tokenize the prompt
+inputs = tokenizer(prompt, return_tensors="pt").to(device)
+
+# generate
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=8192,
+        return_dict_in_generate=True,
+        output_scores=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+# compute reward
+logits = outputs.logits[0, -2, :]
+yes_logit, no_logit = logits[yes_id].item(), logits[no_id].item()
+reward = math.exp(yes_logit) / (math.exp(yes_logit) + math.exp(no_logit))
+```
+
+## Citation
+
+```
+@article{multi-rm,
+  title   = {Rethinking Reward Models for Multi-Domain Test-Time Scaling},
+  author  = {Lee, Dong Bok and Lee, Seanie and Park, Sangwoo and Kang, Minki and Baek, Jinheon and Kim, Dongki and Wagner, Dominik and Jin, Jiongdao and Lee, Heejun and Bocklet, Tobias and Wang, Jinyu and Fu, Jingjing and Hwang, Sung Ju and Bian, Jiang and Song, Lei},
+  journal = {arXiv preprint arXiv:2510.00492},
+  year    = {2025}
+}
+```
\ No newline at end of file
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000..aebc730
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,10 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
+' + '```json' + '
+' + tool['function']['arguments'] + '
+' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'
+' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
+' + '```json' + '
+' + tool['function']['arguments'] + '
+' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
+<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>
+'}}{% endif %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..635364f
--- /dev/null
+++ b/config.json
@@ -0,0 +1,78 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..7a02497
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.53.0"
+}
diff --git a/model-00001-of-00012.safetensors b/model-00001-of-00012.safetensors
new file mode 100644
index 0000000..b7d0d48
--- /dev/null
+++ b/model-00001-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cf8340e9ad4c1ec1daa76a90ee15192695a1bcb30477437c4772771ca2730c
+size 4750149992
diff --git a/model-00002-of-00012.safetensors b/model-00002-of-00012.safetensors
new file mode 100644
index 0000000..c974968
--- /dev/null
+++ b/model-00002-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023166a6bb6f5d41c0ceab4d7339eec9b8a11f0dc386dfb120332e8c74c4f7f2
+size 4970575640
diff --git a/model-00003-of-00012.safetensors b/model-00003-of-00012.safetensors
new file mode 100644
index 0000000..3bb3cba
--- /dev/null
+++ b/model-00003-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c88691fb58f018f02386bf96703951ebcdec8197fd7bb69b79fa2fb1cd79ac0
+size 4939106528
diff --git a/model-00004-of-00012.safetensors b/model-00004-of-00012.safetensors
new file mode 100644
index 0000000..1ed1eef
--- /dev/null
+++ b/model-00004-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a61b406b6949e19b48fa3d853658844efd7b2f2c9c0d0e76f166a2ca6259ad0b
+size 4970575688
diff --git a/model-00005-of-00012.safetensors b/model-00005-of-00012.safetensors
new file mode 100644
index 0000000..45caa04
--- /dev/null
+++ b/model-00005-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae7d97f2cbaf500a5cbbab428d40b5c3cdb32e3da1014bf299793637a45ef92
+size 4939106568
diff --git a/model-00006-of-00012.safetensors b/model-00006-of-00012.safetensors
new file mode 100644
index 0000000..0b299c3
--- /dev/null
+++ b/model-00006-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7126a0fafefad6fdd8b29f64cd81cc7ec82a0a2ebeace54575d089f6f53e95b4
+size 4970575688
diff --git a/model-00007-of-00012.safetensors b/model-00007-of-00012.safetensors
new file mode 100644
index 0000000..be27a79
--- /dev/null
+++ b/model-00007-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a645d00ba08bbd1a345890926be6a806ccb12fab60fd9cd636e7a6a3ffa8a503
+size 4939106568
diff --git a/model-00008-of-00012.safetensors b/model-00008-of-00012.safetensors
new file mode 100644
index 0000000..df681db
--- /dev/null
+++ b/model-00008-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7058d39a48ffbb8de5b2b111245e229a26b0aa541ef86f5fcb6c42811fc245
+size 4970575688
diff --git a/model-00009-of-00012.safetensors b/model-00009-of-00012.safetensors
new file mode 100644
index 0000000..52e68f4
--- /dev/null
+++ b/model-00009-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219667ffe692550159341f41038adb3992173cdbd1f57cc96b72e027ecbcf6c2
+size 4939106568
diff --git a/model-00010-of-00012.safetensors b/model-00010-of-00012.safetensors
new file mode 100644
index 0000000..30e9e25
--- /dev/null
+++ b/model-00010-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e0c69fec43370332c377d4d14d5cbc58d3e91198c4fafc98ed9cd72f209b1f
+size 4970575688
diff --git a/model-00011-of-00012.safetensors b/model-00011-of-00012.safetensors
new file mode 100644
index 0000000..b99d2bb
--- /dev/null
+++ b/model-00011-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3ccc305a0654a48819b03f9ac8380f9a27a5a65e8329ee1a409183c25ad6ac
+size 4939106568
diff --git a/model-00012-of-00012.safetensors b/model-00012-of-00012.safetensors
new file mode 100644
index 0000000..18e8f0f
--- /dev/null
+++ b/model-00012-of-00012.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2862317ad5a815ba19b18e902db173f81cdfc0d4923268d36868b39472022ae
+size 4781639680
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..356ef24
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,587 @@
+{
+  "metadata": {
+    "total_parameters": 14770033664,
+    "total_size": 59080134656
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00012-of-00012.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00007-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00008-of-00012.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00010-of-00012.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00011-of-00012.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00012-of-00012.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.norm.weight": "model-00012-of-00012.safetensors"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..1d385d6
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..1a2db24
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..d252dd4
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}