Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,56 +1,16 @@
 ---
-license: apache-2.0
-datasets:
-- CycloneDX/cdx-docs
+base_model: unsloth/Qwen2.5-Coder-14B-Instruct
 language:
 - en
-base_model:
-- unsloth/Qwen2.5-Coder-14B-Instruct
 library_name: mlx
+license: apache-2.0
 tags:
-- cyclonedx
-- cdxgen
-- sbom
-- security
-- purl
-- obom
-- ml-bom
-- cbom
+- unsloth
+- transformers
+- code
+- qwen
+- qwen-coder
+- codeqwen
+- mlx
+pipeline_tag: text-generation
 ---
-
-**PREVIEW RELEASE**
-
-## Testing with LM Studio
-
-Use [LM Studio](https://lmstudio.ai/docs/basics/download-model) to download and test this model. Search for `CycloneDX/cdx1-mlx` (Full version) or `CycloneDX/cdx1-mlx-8bit` (Recommended).
-
-Use the below configurations:
-
-```
-System Prompt: `You are a helpful assistant to the user.` Use Prompt [Template](https://lmstudio.ai/docs/advanced/prompt-template).
-Temperature: 0.05
-Max tokens: 16000 or 32000
-Context length: 16000
-```
-
-## Testing with mlx
-
-Install [miniconda](https://docs.anaconda.com/miniconda/install/) or Python 3.12
-
-```
-conda create --name cdx1-mlx python=3.12
-conda activate cdx1-mlx
-pip install mlx
-```
-
-LLM Inference from the CLI.
-
-```shell
-mlx_lm.generate --model CycloneDX/cdx1-mlx --system-prompt "You are a helpful assistant to the user." --prompt "tell me about cdxgen" --temp 0.05
-```
-
-Use the 8 bit version for better speed and performance.
-
-```shell
-mlx_lm.generate --model CycloneDX/cdx1-mlx-8bit --system-prompt "You are a helpful assistant to the user." --prompt "tell me about cdxgen" --temp 0.05
-```

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 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
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -1,31 +1,29 @@
 {
     "architectures": [
-        "LlamaForCausalLM"
+        "Qwen2ForCausalLM"
     ],
-    "attention_bias": false,
     "attention_dropout": 0.0,
-    "bos_token_id": 100257,
-    "eos_token_id": 100265,
-    "head_dim": 128,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 5120,
     "initializer_range": 0.02,
-    "intermediate_size": 17920,
-    "max_position_embeddings": 16384,
-    "mlp_bias": false,
-    "model_type": "llama",
+    "intermediate_size": 13824,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
     "num_attention_heads": 40,
-    "num_hidden_layers": 40,
-    "num_key_value_heads": 10,
-    "original_max_position_embeddings": 16384,
-    "pad_token_id": 100351,
-    "pretraining_tp": 1,
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
-    "rope_theta": 250000,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151665,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
     "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.47.1",
+    "transformers_version": "4.44.2",
+    "unsloth_fixed": true,
     "use_cache": true,
-    "vocab_size": 100352
+    "use_sliding_window": false,
+    "vocab_size": 152064
 }

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151665,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885edaf6ff1f34851691ce41248813760645b9720a4f347cb06017e7774191de
-size 5248252582
+oid sha256:78ce05411a483549f826255aad228743f26f6f980f3092f97658ea3efea6f0fd
+size 5269326976

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d497f7cfea1939ae869e5db3e6c9c5ee0464b6c5b8107e5adf42618b7d6ed9
-size 5321694956
+oid sha256:8c57e446239a0b0300b6ac48fb5ed1b4f27887bf23bb9500c9225c1db00957d9
+size 5363828073

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543d2532beeac4b1d20fd094778306a3f756033244325322306d308246769f9d
-size 5269245825
+oid sha256:87a16207f90e2fe13a5346aa7c0018dc2a692372731c8453b1e40438956118d1
+size 5363828102

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952b38c08240be4109358bb1f529c46eec7cc7eb5ca4c99cbbe3dd009250ee3e
-size 5269266538
+oid sha256:cbc8790bb8a6ac2780c22b2161533a7adcf9141190757b6a55178f8655167957
+size 5237963142

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34a75a6526b898527a5ac22d4a5a63243c841f5ab90d1fb6f87a3eaa468be6f
-size 5269266536
+oid sha256:b90ffe283cbbae545160eb4843d7d5e06156f93dc913499c71f258ee994c2e73
+size 5363828102

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322e14ab9528ecc814cf162103b9f12ae0cda663f461c87f2b17a5e0a3957af2
-size 2941330259
+oid sha256:d61ef902a921a72e37beb8f7759aec03d36700a6b1ee9f47c01438386cad3016
+size 2941359481

model.safetensors.index.json

@@ -1,6 +1,7 @@
 {
     "metadata": {
-        "total_size": 29319014400
+        "total_size": 29540067328,
+        "total_parameters": 14770033664
     },
     "weight_map": {
         "lm_head.weight": "model-00006-of-00006.safetensors",
@@ -10,360 +11,576 @@
         "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
         "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
         "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
         "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
         "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
         "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
         "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
         "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
         "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
         "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
         "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
         "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
         "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
         "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
         "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
         "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
         "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
         "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
         "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
         "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
         "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
         "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
         "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
         "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
         "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
         "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
         "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
         "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
         "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
         "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
         "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
         "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
         "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
         "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
         "model.norm.weight": "model-00006-of-00006.safetensors"
     }

special_tokens_map.json

@@ -1,27 +1,28 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": 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|>"
+  ],
   "eos_token": {
     "content": "<|im_end|>",
-    "lstrip": true,
+    "lstrip": false,
     "normalized": false,
-    "rstrip": true,
+    "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|dummy_87|>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "�",
+    "content": "<|PAD_TOKEN|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,791 +1,216 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "5809": {
-      "content": "�",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100256": {
-      "content": "<|dummy_0|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100257": {
-      "content": "<|endoftext|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100258": {
-      "content": "<|fim_prefix|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100259": {
-      "content": "<|fim_middle|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100260": {
-      "content": "<|fim_suffix|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100261": {
-      "content": "<|dummy_1|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100262": {
-      "content": "<|dummy_2|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100263": {
-      "content": "<|dummy_3|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100264": {
+    "151644": {
       "content": "<|im_start|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100265": {
+    "151645": {
       "content": "<|im_end|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100266": {
-      "content": "<|im_sep|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100267": {
-      "content": "<|dummy_4|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100268": {
-      "content": "<|dummy_5|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100269": {
-      "content": "<|dummy_6|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100270": {
-      "content": "<|dummy_7|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100271": {
-      "content": "<|dummy_8|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100272": {
-      "content": "<|dummy_9|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100273": {
-      "content": "<|dummy_10|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100274": {
-      "content": "<|dummy_11|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100275": {
-      "content": "<|dummy_12|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100276": {
-      "content": "<|endofprompt|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100277": {
-      "content": "<|dummy_13|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100278": {
-      "content": "<|dummy_14|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100279": {
-      "content": "<|dummy_15|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100280": {
-      "content": "<|dummy_16|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100281": {
-      "content": "<|dummy_17|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100282": {
-      "content": "<|dummy_18|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100283": {
-      "content": "<|dummy_19|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100284": {
-      "content": "<|dummy_20|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100285": {
-      "content": "<|dummy_21|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100286": {
-      "content": "<|dummy_22|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100287": {
-      "content": "<|dummy_23|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100288": {
-      "content": "<|dummy_24|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100289": {
-      "content": "<|dummy_25|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100290": {
-      "content": "<|dummy_26|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100291": {
-      "content": "<|dummy_27|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100292": {
-      "content": "<|dummy_28|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100293": {
-      "content": "<|dummy_29|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100294": {
-      "content": "<|dummy_30|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100295": {
-      "content": "<|dummy_31|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100296": {
-      "content": "<|dummy_32|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100297": {
-      "content": "<|dummy_33|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100298": {
-      "content": "<|dummy_34|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100299": {
-      "content": "<|dummy_35|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100300": {
-      "content": "<|dummy_36|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100301": {
-      "content": "<|dummy_37|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100302": {
-      "content": "<|dummy_38|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100303": {
-      "content": "<|dummy_39|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100304": {
-      "content": "<|dummy_40|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100305": {
-      "content": "<|dummy_41|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100306": {
-      "content": "<|dummy_42|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100307": {
-      "content": "<|dummy_43|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100308": {
-      "content": "<|dummy_44|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100309": {
-      "content": "<|dummy_45|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100310": {
-      "content": "<|dummy_46|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100311": {
-      "content": "<|dummy_47|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100312": {
-      "content": "<|dummy_48|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100313": {
-      "content": "<|dummy_49|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100314": {
-      "content": "<|dummy_50|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100315": {
-      "content": "<|dummy_51|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100316": {
-      "content": "<|dummy_52|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100317": {
-      "content": "<|dummy_53|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100318": {
-      "content": "<|dummy_54|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100319": {
-      "content": "<|dummy_55|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100320": {
-      "content": "<|dummy_56|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100321": {
-      "content": "<|dummy_57|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100322": {
-      "content": "<|dummy_58|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100323": {
-      "content": "<|dummy_59|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100324": {
-      "content": "<|dummy_60|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100325": {
-      "content": "<|dummy_61|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100326": {
-      "content": "<|dummy_62|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100327": {
-      "content": "<|dummy_63|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100328": {
-      "content": "<|dummy_64|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100329": {
-      "content": "<|dummy_65|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100330": {
-      "content": "<|dummy_66|>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "100331": {
-      "content": "<|dummy_67|>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100332": {
-      "content": "<|dummy_68|>",
-      "lstrip": true,
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100333": {
-      "content": "<|dummy_69|>",
-      "lstrip": true,
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100334": {
-      "content": "<|dummy_70|>",
-      "lstrip": true,
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100335": {
-      "content": "<|dummy_71|>",
-      "lstrip": true,
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100336": {
-      "content": "<|dummy_72|>",
-      "lstrip": true,
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100337": {
-      "content": "<|dummy_73|>",
-      "lstrip": true,
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100338": {
-      "content": "<|dummy_74|>",
-      "lstrip": true,
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100339": {
-      "content": "<|dummy_75|>",
-      "lstrip": true,
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100340": {
-      "content": "<|dummy_76|>",
-      "lstrip": true,
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100341": {
-      "content": "<|dummy_77|>",
-      "lstrip": true,
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100342": {
-      "content": "<|dummy_78|>",
-      "lstrip": true,
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100343": {
-      "content": "<|dummy_79|>",
-      "lstrip": true,
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100344": {
-      "content": "<|dummy_80|>",
-      "lstrip": true,
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100345": {
-      "content": "<|dummy_81|>",
-      "lstrip": true,
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100346": {
-      "content": "<|dummy_82|>",
-      "lstrip": true,
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100347": {
-      "content": "<|dummy_83|>",
-      "lstrip": true,
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100348": {
-      "content": "<|dummy_84|>",
-      "lstrip": true,
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100349": {
-      "content": "<|dummy_85|>",
-      "lstrip": true,
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100350": {
-      "content": "<|dummy_86|>",
-      "lstrip": true,
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "100351": {
-      "content": "<|dummy_87|>",
-      "lstrip": true,
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
+  "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": 16384,
-  "pad_token": "<|dummy_87|>",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
   "padding_side": "left",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "�"
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }