From a4a512151b0339314bed5f2b7615441c786c8e09 Mon Sep 17 00:00:00 2001
From: ModelHub XC <noreply@modelhub.org.cn>
Date: Tue, 28 Jul 2026 22:15:10 +0800
Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?=
 =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?=
 =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Model: yamatazen/Qwen3-HereticLM-4B
Source: Original Platform
---
 .gitattributes                   |  36 +++
 README.md                        |  39 +++
 added_tokens.json                |  28 +++
 config.json                      |  71 ++++++
 generation_config.json           |  13 +
 mergekit_config.yml              |   8 +
 model-00001-of-00009.safetensors |   3 +
 model-00002-of-00009.safetensors |   3 +
 model-00003-of-00009.safetensors |   3 +
 model-00004-of-00009.safetensors |   3 +
 model-00005-of-00009.safetensors |   3 +
 model-00006-of-00009.safetensors |   3 +
 model-00007-of-00009.safetensors |   3 +
 model-00008-of-00009.safetensors |   3 +
 model-00009-of-00009.safetensors |   3 +
 model.safetensors.index.json     | 406 +++++++++++++++++++++++++++++++
 special_tokens_map.json          |  31 +++
 tokenizer.json                   |   3 +
 tokenizer_config.json            | 239 ++++++++++++++++++
 19 files changed, 901 insertions(+)
 create mode 100644 .gitattributes
 create mode 100644 README.md
 create mode 100644 added_tokens.json
 create mode 100644 config.json
 create mode 100644 generation_config.json
 create mode 100644 mergekit_config.yml
 create mode 100644 model-00001-of-00009.safetensors
 create mode 100644 model-00002-of-00009.safetensors
 create mode 100644 model-00003-of-00009.safetensors
 create mode 100644 model-00004-of-00009.safetensors
 create mode 100644 model-00005-of-00009.safetensors
 create mode 100644 model-00006-of-00009.safetensors
 create mode 100644 model-00007-of-00009.safetensors
 create mode 100644 model-00008-of-00009.safetensors
 create mode 100644 model-00009-of-00009.safetensors
 create mode 100644 model.safetensors.index.json
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer.json
 create mode 100644 tokenizer_config.json

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..ab567b2
--- /dev/null
+++ b/README.md
@@ -0,0 +1,39 @@
+---
+base_model:
+- yamatazen/Qwen3-4B-HereticCPT
+- heretic-org/Qwen3-4B-Instruct-2507-heretic
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: apache-2.0
+---
+# Qwen3-HereticLM-4B
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [yamatazen/Qwen3-4B-HereticCPT](https://huggingface.co/yamatazen/Qwen3-4B-HereticCPT)
+* [heretic-org/Qwen3-4B-Instruct-2507-heretic](https://huggingface.co/heretic-org/Qwen3-4B-Instruct-2507-heretic)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: slerp
+dtype: bfloat16
+out_dtype: bfloat16
+base_model: heretic-org/Qwen3-4B-Instruct-2507-heretic
+models:
+  - model: yamatazen/Qwen3-4B-HereticCPT
+parameters:
+  t: 0.5
+```
\ No newline at end of file
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..b54f913
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..97dbdc8
--- /dev/null
+++ b/config.json
@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..9a7dcbe
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.6"
+}
diff --git a/mergekit_config.yml b/mergekit_config.yml
new file mode 100644
index 0000000..7df8f46
--- /dev/null
+++ b/mergekit_config.yml
@@ -0,0 +1,8 @@
+merge_method: slerp
+dtype: bfloat16
+out_dtype: bfloat16
+base_model: heretic-org/Qwen3-4B-Instruct-2507-heretic
+models:
+  - model: yamatazen/Qwen3-4B-HereticCPT
+parameters:
+  t: 0.5
\ No newline at end of file
diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors
new file mode 100644
index 0000000..42e7506
--- /dev/null
+++ b/model-00001-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c9313a2d9b11f393facfa9800e9b3bd00e4e9c6081e09ad36bfd02437e6a3c
+size 979780560
diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors
new file mode 100644
index 0000000..92de2ec
--- /dev/null
+++ b/model-00002-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef07d99cffe6f4db90e9eb638ed79de93c117842541cbd9388750d6fd5fee5c
+size 983094568
diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors
new file mode 100644
index 0000000..b33395a
--- /dev/null
+++ b/model-00003-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e756aa44d0133b976e0d6c526795e151631faf0d99be700cafbb757522668d
+size 988342432
diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors
new file mode 100644
index 0000000..b121515
--- /dev/null
+++ b/model-00004-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856d4a371554f3b71b3c94a92d1a5e4ea557e9447d3733841af31f6ede119723
+size 954258352
diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors
new file mode 100644
index 0000000..8e549e3
--- /dev/null
+++ b/model-00005-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab05a4c3c9adf4fd7771a0d9ce9502b05635cda12d644caa8f89ed6bb69924a9
+size 959506960
diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors
new file mode 100644
index 0000000..9a99fcc
--- /dev/null
+++ b/model-00006-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8f656dd7cf1b3a26a0300f13bfe51ca34c896df47cc2ea532823dd30e3f178
+size 959506952
diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors
new file mode 100644
index 0000000..a33184e
--- /dev/null
+++ b/model-00007-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be21e9756dd944b1532acd5ac10b0253c9a97dda60c3ad383ba596f66823cac4
+size 983094576
diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors
new file mode 100644
index 0000000..d5f49a0
--- /dev/null
+++ b/model-00008-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2918cb79cd75f44e89f51ce1d426d9d492185585c4ec771cdbf4becd73498668
+size 988342384
diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors
new file mode 100644
index 0000000..9052f81
--- /dev/null
+++ b/model-00009-of-00009.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c3c7bbe8ece7f4ef2a6c94c2378267a54e5235c596e5655a5c4c9573f2e53c
+size 249054736
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..fccd197
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 8044936192,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}
\ No newline at end of file
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..ac23c0a
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..f9abfc3
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
+size 11422821
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..c9fc122
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}