scottlowry commited on about 20 hours ago

Commit

842b8c8

0 Parent(s):

Super-squash branch 'main' using huggingface_hub

Browse files

Files changed (18) hide show

.gitattributes +36 -0
README.md +39 -0
chat_template.jinja +150 -0
config.json +0 -0
generation_config.json +12 -0
merges.txt +0 -0
model-00001-of-00005.safetensors +3 -0
model-00002-of-00005.safetensors +3 -0
model-00003-of-00005.safetensors +3 -0
model-00004-of-00005.safetensors +3 -0
model-00005-of-00005.safetensors +3 -0
model.safetensors.index.json +0 -0
oq_imatrix_report.json +594 -0
preprocessor_config.json +21 -0
processor_config.json +60 -0
tokenizer.json +3 -0
tokenizer_config.json +305 -0
vocab.json +0 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,36 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,39 @@

+---
+library_name: mlx
+tags:
+- mlx
+- oq
+- quantized
+- mtp
+base_model:
+- ornith-ai/Ornith-1.5-35B-A3B
+---
+# Ornith-1.5-35B-A3B-oQ4e-fp16-mtp
+> [!NOTE]
+> **Updated 2026-11-11:** Re-quantized with oMLX v0.7.4.dev1. Please re-download if you have an earlier copy.
+This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.7.4.dev1) mixed-precision quantization.
+The effective average is 5.124 bits/weight for the complete checkpoint.
+## Quantization and Bit Distribution
+| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
+|---|---|---|---|---|
+| Affine 4-bit, group 64 | 33.018B | 91.838% | 17.297 GiB | 4.50 |
+| Affine 8-bit, group 128 | 0.129B | 0.359% | 0.124 GiB | 8.25 |
+| Affine 8-bit, group 64 | 2.328B | 6.474% | 2.303 GiB | 8.50 |
+| FP16 | 0.031B | 0.086% | 0.058 GiB | 16.00 |
+| FP32 | 0.447B | 1.242% | 1.664 GiB | 32.00 |
+| **Total** | **35.952B** | **100%** | **21.445 GiB** | **5.124** |
+## Storage Breakdown
+| Component | Logical weights | Storage |
+|---|---|---|
+| Language model | 34.661B | 20.738 GB / 19.313 GiB |
+| Vision | 0.447B | 1.786 GB / 1.664 GiB |
+| MTP head | 0.845B | 0.503 GB / 0.468 GiB |
+| **Total** | **35.952B** | **23.027 GB / 21.445 GiB** |

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,150 @@

+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json ADDED Viewed

The diff for this file is too large to render. See raw diff

generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+    "bos_token_id": 248044,
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "pad_token_id": 248044,
+    "temperature": 1.0,
+    "top_k": 20,
+    "top_p": 0.95
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model-00001-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c2287939e8581a71d61ed06094b960bbe224f6a6166a4f3216ead7cce3f681
+size 5058738477

model-00002-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:675f910851cf859be1adb3741f2a16aaa26810c09778142c53996e52db63340f
+size 5133842356

model-00003-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:24912c4779daed6a6ba9679390a56265bcaaf014648655676c8f481c526b06ad
+size 5133842434

model-00004-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:918d5ae38d7bb3c36cc5d5a90607a5c9daf6885ccf30c4c9c7e2b1c5c4095b25
+size 5133842440

model-00005-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:68c5c67959b9dd6a47bd50c04bbf9433504fca9ee15c537706eecab4e175be3b
+size 2566921167

model.safetensors.index.json ADDED Viewed

The diff for this file is too large to render. See raw diff

oq_imatrix_report.json ADDED Viewed

	@@ -0,0 +1,594 @@

+{
+  "enabled": true,
+  "cache_path": "/Users/scott/.omlx/models/.oqe_imatrix/Ornith-1.5-35B-A3B-303585a1f73e-s128-l512.npz",
+  "cache_reused": true,
+  "entry_count": 523,
+  "calib_dataset": "oqe_code_multilingual",
+  "collection": {
+    "dataset": "oqe_code_multilingual",
+    "requested_samples": 128,
+    "seq_length": 512,
+    "adaptive": true,
+    "adaptive_step_samples": 128,
+    "adaptive_max_samples": 1024,
+    "available_samples": 1024,
+    "micro_batch_size": 16,
+    "micro_batches": 8,
+    "batch_plan": {
+      "micro_batch_size": 16,
+      "estimated_sample_bytes": 33554432,
+      "capture_budget_bytes": 805306368,
+      "system_available_bytes": 233105244160,
+      "metal_available_bytes": 261128382770,
+      "live_available_bytes": 233105244160,
+      "model_bytes": 71903871064,
+      "remaining_available_bytes": 161201373096,
+      "fits_one_sample": true,
+      "hidden_size": 2048,
+      "num_experts": 256,
+      "top_k": 8,
+      "gemma4_state_bytes": 0,
+      "num_hidden_layers": 40,
+      "num_kv_shared_layers": 0,
+      "per_layer_input_size": 0
+    },
+    "processed_samples": 128,
+    "model_class": "mlx_vlm.models.qwen3_5_moe.qwen3_5_moe.Model",
+    "layer_model_class": "mlx_vlm.models.qwen3_5_moe.language.Qwen3_5MoeModel",
+    "layer_model_type": "qwen3_5_moe_text",
+    "layer_count": 40,
+    "layer_state_kind": "generic",
+    "successful_layer_forwards": 320,
+    "skipped_layer_forwards": 0,
+    "mtp_head_forwards": 8,
+    "installed_modules": 634,
+    "capture_module_classes": {
+      "Linear": 511,
+      "SwitchLinear": 123
+    },
+    "switch_capture_modules": 123,
+    "requires_expert_counts": true,
+    "coverage_sufficient": true,
+    "collection_sufficient": true,
+    "coverage": {
+      "has_expert_counts": true,
+      "expert_modules": 123,
+      "total_experts": 31488,
+      "active_experts": 31488,
+      "zero_count_experts": 0,
+      "active_ratio": 1.0,
+      "min_count": 71,
+      "p05_count": 592.0,
+      "p10_count": 753.0,
+      "median_count": 1670.0,
+      "max_count": 35773,
+      "min_required_count": 16,
+      "required_percentile": 5
+    },
+    "rounds": [
+      {
+        "processed_samples": 128,
+        "coverage_sufficient": true,
+        "collection_sufficient": true,
+        "coverage": {
+          "has_expert_counts": true,
+          "expert_modules": 123,
+          "total_experts": 31488,
+          "active_experts": 31488,
+          "zero_count_experts": 0,
+          "active_ratio": 1.0,
+          "min_count": 71,
+          "p05_count": 592.0,
+          "p10_count": 753.0,
+          "median_count": 1670.0,
+          "max_count": 35773,
+          "min_required_count": 16,
+          "required_percentile": 5
+        }
+      }
+    ]
+  },
+  "expert_coverage": {
+    "has_expert_counts": true,
+    "expert_modules": 123,
+    "total_experts": 31488,
+    "active_experts": 31488,
+    "zero_count_experts": 0,
+    "active_ratio": 1.0,
+    "min_count": 71,
+    "p05_count": 592.0,
+    "p10_count": 753.0,
+    "median_count": 1670.0,
+    "max_count": 35773,
+    "min_required_count": 16,
+    "required_percentile": 5
+  },
+  "applied": [
+    "language_model.model.layers.0.linear_attn.in_proj_a",
+    "language_model.model.layers.0.linear_attn.in_proj_b",
+    "language_model.model.layers.0.linear_attn.in_proj_qkv",
+    "language_model.model.layers.0.linear_attn.in_proj_z",
+    "language_model.model.layers.0.linear_attn.out_proj",
+    "language_model.model.layers.0.mlp.shared_expert.down_proj",
+    "language_model.model.layers.0.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.0.mlp.shared_expert.up_proj",
+    "language_model.model.layers.0.mlp.shared_expert_gate",
+    "language_model.model.layers.0.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.0.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.0.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.1.linear_attn.in_proj_a",
+    "language_model.model.layers.1.linear_attn.in_proj_b",
+    "language_model.model.layers.1.linear_attn.in_proj_qkv",
+    "language_model.model.layers.1.linear_attn.in_proj_z",
+    "language_model.model.layers.1.linear_attn.out_proj",
+    "language_model.model.layers.1.mlp.shared_expert.down_proj",
+    "language_model.model.layers.1.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.1.mlp.shared_expert.up_proj",
+    "language_model.model.layers.1.mlp.shared_expert_gate",
+    "language_model.model.layers.1.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.1.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.1.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.10.linear_attn.in_proj_a",
+    "language_model.model.layers.10.linear_attn.in_proj_b",
+    "language_model.model.layers.10.linear_attn.in_proj_qkv",
+    "language_model.model.layers.10.linear_attn.in_proj_z",
+    "language_model.model.layers.10.linear_attn.out_proj",
+    "language_model.model.layers.10.mlp.shared_expert.down_proj",
+    "language_model.model.layers.10.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.10.mlp.shared_expert.up_proj",
+    "language_model.model.layers.10.mlp.shared_expert_gate",
+    "language_model.model.layers.10.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.10.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.10.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.11.mlp.shared_expert.down_proj",
+    "language_model.model.layers.11.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.11.mlp.shared_expert.up_proj",
+    "language_model.model.layers.11.mlp.shared_expert_gate",
+    "language_model.model.layers.11.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.11.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.11.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.11.self_attn.k_proj",
+    "language_model.model.layers.11.self_attn.o_proj",
+    "language_model.model.layers.11.self_attn.q_proj",
+    "language_model.model.layers.11.self_attn.v_proj",
+    "language_model.model.layers.12.linear_attn.in_proj_a",
+    "language_model.model.layers.12.linear_attn.in_proj_b",
+    "language_model.model.layers.12.linear_attn.in_proj_qkv",
+    "language_model.model.layers.12.linear_attn.in_proj_z",
+    "language_model.model.layers.12.linear_attn.out_proj",
+    "language_model.model.layers.12.mlp.shared_expert.down_proj",
+    "language_model.model.layers.12.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.12.mlp.shared_expert.up_proj",
+    "language_model.model.layers.12.mlp.shared_expert_gate",
+    "language_model.model.layers.12.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.12.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.12.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.13.linear_attn.in_proj_a",
+    "language_model.model.layers.13.linear_attn.in_proj_b",
+    "language_model.model.layers.13.linear_attn.in_proj_qkv",
+    "language_model.model.layers.13.linear_attn.in_proj_z",
+    "language_model.model.layers.13.linear_attn.out_proj",
+    "language_model.model.layers.13.mlp.shared_expert.down_proj",
+    "language_model.model.layers.13.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.13.mlp.shared_expert.up_proj",
+    "language_model.model.layers.13.mlp.shared_expert_gate",
+    "language_model.model.layers.13.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.13.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.13.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.14.linear_attn.in_proj_a",
+    "language_model.model.layers.14.linear_attn.in_proj_b",
+    "language_model.model.layers.14.linear_attn.in_proj_qkv",
+    "language_model.model.layers.14.linear_attn.in_proj_z",
+    "language_model.model.layers.14.linear_attn.out_proj",
+    "language_model.model.layers.14.mlp.shared_expert.down_proj",
+    "language_model.model.layers.14.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.14.mlp.shared_expert.up_proj",
+    "language_model.model.layers.14.mlp.shared_expert_gate",
+    "language_model.model.layers.14.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.14.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.14.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.15.mlp.shared_expert.down_proj",
+    "language_model.model.layers.15.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.15.mlp.shared_expert.up_proj",
+    "language_model.model.layers.15.mlp.shared_expert_gate",
+    "language_model.model.layers.15.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.15.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.15.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.15.self_attn.k_proj",
+    "language_model.model.layers.15.self_attn.o_proj",
+    "language_model.model.layers.15.self_attn.q_proj",
+    "language_model.model.layers.15.self_attn.v_proj",
+    "language_model.model.layers.16.linear_attn.in_proj_a",
+    "language_model.model.layers.16.linear_attn.in_proj_b",
+    "language_model.model.layers.16.linear_attn.in_proj_qkv",
+    "language_model.model.layers.16.linear_attn.in_proj_z",
+    "language_model.model.layers.16.linear_attn.out_proj",
+    "language_model.model.layers.16.mlp.shared_expert.down_proj",
+    "language_model.model.layers.16.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.16.mlp.shared_expert.up_proj",
+    "language_model.model.layers.16.mlp.shared_expert_gate",
+    "language_model.model.layers.16.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.16.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.16.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.17.linear_attn.in_proj_a",
+    "language_model.model.layers.17.linear_attn.in_proj_b",
+    "language_model.model.layers.17.linear_attn.in_proj_qkv",
+    "language_model.model.layers.17.linear_attn.in_proj_z",
+    "language_model.model.layers.17.linear_attn.out_proj",
+    "language_model.model.layers.17.mlp.shared_expert.down_proj",
+    "language_model.model.layers.17.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.17.mlp.shared_expert.up_proj",
+    "language_model.model.layers.17.mlp.shared_expert_gate",
+    "language_model.model.layers.17.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.17.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.17.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.18.linear_attn.in_proj_a",
+    "language_model.model.layers.18.linear_attn.in_proj_b",
+    "language_model.model.layers.18.linear_attn.in_proj_qkv",
+    "language_model.model.layers.18.linear_attn.in_proj_z",
+    "language_model.model.layers.18.linear_attn.out_proj",
+    "language_model.model.layers.18.mlp.shared_expert.down_proj",
+    "language_model.model.layers.18.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.18.mlp.shared_expert.up_proj",
+    "language_model.model.layers.18.mlp.shared_expert_gate",
+    "language_model.model.layers.18.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.18.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.18.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.19.mlp.shared_expert.down_proj",
+    "language_model.model.layers.19.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.19.mlp.shared_expert.up_proj",
+    "language_model.model.layers.19.mlp.shared_expert_gate",
+    "language_model.model.layers.19.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.19.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.19.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.19.self_attn.k_proj",
+    "language_model.model.layers.19.self_attn.o_proj",
+    "language_model.model.layers.19.self_attn.q_proj",
+    "language_model.model.layers.19.self_attn.v_proj",
+    "language_model.model.layers.2.linear_attn.in_proj_a",
+    "language_model.model.layers.2.linear_attn.in_proj_b",
+    "language_model.model.layers.2.linear_attn.in_proj_qkv",
+    "language_model.model.layers.2.linear_attn.in_proj_z",
+    "language_model.model.layers.2.linear_attn.out_proj",
+    "language_model.model.layers.2.mlp.shared_expert.down_proj",
+    "language_model.model.layers.2.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.2.mlp.shared_expert.up_proj",
+    "language_model.model.layers.2.mlp.shared_expert_gate",
+    "language_model.model.layers.2.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.2.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.2.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.20.linear_attn.in_proj_a",
+    "language_model.model.layers.20.linear_attn.in_proj_b",
+    "language_model.model.layers.20.linear_attn.in_proj_qkv",
+    "language_model.model.layers.20.linear_attn.in_proj_z",
+    "language_model.model.layers.20.linear_attn.out_proj",
+    "language_model.model.layers.20.mlp.shared_expert.down_proj",
+    "language_model.model.layers.20.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.20.mlp.shared_expert.up_proj",
+    "language_model.model.layers.20.mlp.shared_expert_gate",
+    "language_model.model.layers.20.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.20.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.20.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.21.linear_attn.in_proj_a",
+    "language_model.model.layers.21.linear_attn.in_proj_b",
+    "language_model.model.layers.21.linear_attn.in_proj_qkv",
+    "language_model.model.layers.21.linear_attn.in_proj_z",
+    "language_model.model.layers.21.linear_attn.out_proj",
+    "language_model.model.layers.21.mlp.shared_expert.down_proj",
+    "language_model.model.layers.21.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.21.mlp.shared_expert.up_proj",
+    "language_model.model.layers.21.mlp.shared_expert_gate",
+    "language_model.model.layers.21.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.21.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.21.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.22.linear_attn.in_proj_a",
+    "language_model.model.layers.22.linear_attn.in_proj_b",
+    "language_model.model.layers.22.linear_attn.in_proj_qkv",
+    "language_model.model.layers.22.linear_attn.in_proj_z",
+    "language_model.model.layers.22.linear_attn.out_proj",
+    "language_model.model.layers.22.mlp.shared_expert.down_proj",
+    "language_model.model.layers.22.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.22.mlp.shared_expert.up_proj",
+    "language_model.model.layers.22.mlp.shared_expert_gate",
+    "language_model.model.layers.22.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.22.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.22.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.23.mlp.shared_expert.down_proj",
+    "language_model.model.layers.23.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.23.mlp.shared_expert.up_proj",
+    "language_model.model.layers.23.mlp.shared_expert_gate",
+    "language_model.model.layers.23.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.23.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.23.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.23.self_attn.k_proj",
+    "language_model.model.layers.23.self_attn.o_proj",
+    "language_model.model.layers.23.self_attn.q_proj",
+    "language_model.model.layers.23.self_attn.v_proj",
+    "language_model.model.layers.24.linear_attn.in_proj_a",
+    "language_model.model.layers.24.linear_attn.in_proj_b",
+    "language_model.model.layers.24.linear_attn.in_proj_qkv",
+    "language_model.model.layers.24.linear_attn.in_proj_z",
+    "language_model.model.layers.24.linear_attn.out_proj",
+    "language_model.model.layers.24.mlp.shared_expert.down_proj",
+    "language_model.model.layers.24.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.24.mlp.shared_expert.up_proj",
+    "language_model.model.layers.24.mlp.shared_expert_gate",
+    "language_model.model.layers.24.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.24.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.24.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.25.linear_attn.in_proj_a",
+    "language_model.model.layers.25.linear_attn.in_proj_b",
+    "language_model.model.layers.25.linear_attn.in_proj_qkv",
+    "language_model.model.layers.25.linear_attn.in_proj_z",
+    "language_model.model.layers.25.linear_attn.out_proj",
+    "language_model.model.layers.25.mlp.shared_expert.down_proj",
+    "language_model.model.layers.25.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.25.mlp.shared_expert.up_proj",
+    "language_model.model.layers.25.mlp.shared_expert_gate",
+    "language_model.model.layers.25.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.25.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.25.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.26.linear_attn.in_proj_a",
+    "language_model.model.layers.26.linear_attn.in_proj_b",
+    "language_model.model.layers.26.linear_attn.in_proj_qkv",
+    "language_model.model.layers.26.linear_attn.in_proj_z",
+    "language_model.model.layers.26.linear_attn.out_proj",
+    "language_model.model.layers.26.mlp.shared_expert.down_proj",
+    "language_model.model.layers.26.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.26.mlp.shared_expert.up_proj",
+    "language_model.model.layers.26.mlp.shared_expert_gate",
+    "language_model.model.layers.26.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.26.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.26.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.27.mlp.shared_expert.down_proj",
+    "language_model.model.layers.27.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.27.mlp.shared_expert.up_proj",
+    "language_model.model.layers.27.mlp.shared_expert_gate",
+    "language_model.model.layers.27.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.27.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.27.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.27.self_attn.k_proj",
+    "language_model.model.layers.27.self_attn.o_proj",
+    "language_model.model.layers.27.self_attn.q_proj",
+    "language_model.model.layers.27.self_attn.v_proj",
+    "language_model.model.layers.28.linear_attn.in_proj_a",
+    "language_model.model.layers.28.linear_attn.in_proj_b",
+    "language_model.model.layers.28.linear_attn.in_proj_qkv",
+    "language_model.model.layers.28.linear_attn.in_proj_z",
+    "language_model.model.layers.28.linear_attn.out_proj",
+    "language_model.model.layers.28.mlp.shared_expert.down_proj",
+    "language_model.model.layers.28.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.28.mlp.shared_expert.up_proj",
+    "language_model.model.layers.28.mlp.shared_expert_gate",
+    "language_model.model.layers.28.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.28.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.28.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.29.linear_attn.in_proj_a",
+    "language_model.model.layers.29.linear_attn.in_proj_b",
+    "language_model.model.layers.29.linear_attn.in_proj_qkv",
+    "language_model.model.layers.29.linear_attn.in_proj_z",
+    "language_model.model.layers.29.linear_attn.out_proj",
+    "language_model.model.layers.29.mlp.shared_expert.down_proj",
+    "language_model.model.layers.29.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.29.mlp.shared_expert.up_proj",
+    "language_model.model.layers.29.mlp.shared_expert_gate",
+    "language_model.model.layers.29.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.29.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.29.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.3.mlp.shared_expert.down_proj",
+    "language_model.model.layers.3.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.3.mlp.shared_expert.up_proj",
+    "language_model.model.layers.3.mlp.shared_expert_gate",
+    "language_model.model.layers.3.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.3.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.3.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.3.self_attn.k_proj",
+    "language_model.model.layers.3.self_attn.o_proj",
+    "language_model.model.layers.3.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.v_proj",
+    "language_model.model.layers.30.linear_attn.in_proj_a",
+    "language_model.model.layers.30.linear_attn.in_proj_b",
+    "language_model.model.layers.30.linear_attn.in_proj_qkv",
+    "language_model.model.layers.30.linear_attn.in_proj_z",
+    "language_model.model.layers.30.linear_attn.out_proj",
+    "language_model.model.layers.30.mlp.shared_expert.down_proj",
+    "language_model.model.layers.30.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.30.mlp.shared_expert.up_proj",
+    "language_model.model.layers.30.mlp.shared_expert_gate",
+    "language_model.model.layers.30.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.30.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.30.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.31.mlp.shared_expert.down_proj",
+    "language_model.model.layers.31.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.31.mlp.shared_expert.up_proj",
+    "language_model.model.layers.31.mlp.shared_expert_gate",
+    "language_model.model.layers.31.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.31.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.31.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.31.self_attn.k_proj",
+    "language_model.model.layers.31.self_attn.o_proj",
+    "language_model.model.layers.31.self_attn.q_proj",
+    "language_model.model.layers.31.self_attn.v_proj",
+    "language_model.model.layers.32.linear_attn.in_proj_a",
+    "language_model.model.layers.32.linear_attn.in_proj_b",
+    "language_model.model.layers.32.linear_attn.in_proj_qkv",
+    "language_model.model.layers.32.linear_attn.in_proj_z",
+    "language_model.model.layers.32.linear_attn.out_proj",
+    "language_model.model.layers.32.mlp.shared_expert.down_proj",
+    "language_model.model.layers.32.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.32.mlp.shared_expert.up_proj",
+    "language_model.model.layers.32.mlp.shared_expert_gate",
+    "language_model.model.layers.32.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.32.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.32.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.33.linear_attn.in_proj_a",
+    "language_model.model.layers.33.linear_attn.in_proj_b",
+    "language_model.model.layers.33.linear_attn.in_proj_qkv",
+    "language_model.model.layers.33.linear_attn.in_proj_z",
+    "language_model.model.layers.33.linear_attn.out_proj",
+    "language_model.model.layers.33.mlp.shared_expert.down_proj",
+    "language_model.model.layers.33.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.33.mlp.shared_expert.up_proj",
+    "language_model.model.layers.33.mlp.shared_expert_gate",
+    "language_model.model.layers.33.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.33.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.33.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.34.linear_attn.in_proj_a",
+    "language_model.model.layers.34.linear_attn.in_proj_b",
+    "language_model.model.layers.34.linear_attn.in_proj_qkv",
+    "language_model.model.layers.34.linear_attn.in_proj_z",
+    "language_model.model.layers.34.linear_attn.out_proj",
+    "language_model.model.layers.34.mlp.shared_expert.down_proj",
+    "language_model.model.layers.34.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.34.mlp.shared_expert.up_proj",
+    "language_model.model.layers.34.mlp.shared_expert_gate",
+    "language_model.model.layers.34.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.34.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.34.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.35.mlp.shared_expert.down_proj",
+    "language_model.model.layers.35.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.35.mlp.shared_expert.up_proj",
+    "language_model.model.layers.35.mlp.shared_expert_gate",
+    "language_model.model.layers.35.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.35.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.35.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.35.self_attn.k_proj",
+    "language_model.model.layers.35.self_attn.o_proj",
+    "language_model.model.layers.35.self_attn.q_proj",
+    "language_model.model.layers.35.self_attn.v_proj",
+    "language_model.model.layers.36.linear_attn.in_proj_a",
+    "language_model.model.layers.36.linear_attn.in_proj_b",
+    "language_model.model.layers.36.linear_attn.in_proj_qkv",
+    "language_model.model.layers.36.linear_attn.in_proj_z",
+    "language_model.model.layers.36.linear_attn.out_proj",
+    "language_model.model.layers.36.mlp.shared_expert.down_proj",
+    "language_model.model.layers.36.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.36.mlp.shared_expert.up_proj",
+    "language_model.model.layers.36.mlp.shared_expert_gate",
+    "language_model.model.layers.36.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.36.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.36.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.37.linear_attn.in_proj_a",
+    "language_model.model.layers.37.linear_attn.in_proj_b",
+    "language_model.model.layers.37.linear_attn.in_proj_qkv",
+    "language_model.model.layers.37.linear_attn.in_proj_z",
+    "language_model.model.layers.37.linear_attn.out_proj",
+    "language_model.model.layers.37.mlp.shared_expert.down_proj",
+    "language_model.model.layers.37.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.37.mlp.shared_expert.up_proj",
+    "language_model.model.layers.37.mlp.shared_expert_gate",
+    "language_model.model.layers.37.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.37.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.37.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.38.linear_attn.in_proj_a",
+    "language_model.model.layers.38.linear_attn.in_proj_b",
+    "language_model.model.layers.38.linear_attn.in_proj_qkv",
+    "language_model.model.layers.38.linear_attn.in_proj_z",
+    "language_model.model.layers.38.linear_attn.out_proj",
+    "language_model.model.layers.38.mlp.shared_expert.down_proj",
+    "language_model.model.layers.38.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.38.mlp.shared_expert.up_proj",
+    "language_model.model.layers.38.mlp.shared_expert_gate",
+    "language_model.model.layers.38.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.38.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.38.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.39.mlp.shared_expert.down_proj",
+    "language_model.model.layers.39.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.39.mlp.shared_expert.up_proj",
+    "language_model.model.layers.39.mlp.shared_expert_gate",
+    "language_model.model.layers.39.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.39.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.39.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.39.self_attn.k_proj",
+    "language_model.model.layers.39.self_attn.o_proj",
+    "language_model.model.layers.39.self_attn.q_proj",
+    "language_model.model.layers.39.self_attn.v_proj",
+    "language_model.model.layers.4.linear_attn.in_proj_a",
+    "language_model.model.layers.4.linear_attn.in_proj_b",
+    "language_model.model.layers.4.linear_attn.in_proj_qkv",
+    "language_model.model.layers.4.linear_attn.in_proj_z",
+    "language_model.model.layers.4.linear_attn.out_proj",
+    "language_model.model.layers.4.mlp.shared_expert.down_proj",
+    "language_model.model.layers.4.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.4.mlp.shared_expert.up_proj",
+    "language_model.model.layers.4.mlp.shared_expert_gate",
+    "language_model.model.layers.4.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.4.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.4.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.5.linear_attn.in_proj_a",
+    "language_model.model.layers.5.linear_attn.in_proj_b",
+    "language_model.model.layers.5.linear_attn.in_proj_qkv",
+    "language_model.model.layers.5.linear_attn.in_proj_z",
+    "language_model.model.layers.5.linear_attn.out_proj",
+    "language_model.model.layers.5.mlp.shared_expert.down_proj",
+    "language_model.model.layers.5.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.5.mlp.shared_expert.up_proj",
+    "language_model.model.layers.5.mlp.shared_expert_gate",
+    "language_model.model.layers.5.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.5.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.5.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.6.linear_attn.in_proj_a",
+    "language_model.model.layers.6.linear_attn.in_proj_b",
+    "language_model.model.layers.6.linear_attn.in_proj_qkv",
+    "language_model.model.layers.6.linear_attn.in_proj_z",
+    "language_model.model.layers.6.linear_attn.out_proj",
+    "language_model.model.layers.6.mlp.shared_expert.down_proj",
+    "language_model.model.layers.6.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.6.mlp.shared_expert.up_proj",
+    "language_model.model.layers.6.mlp.shared_expert_gate",
+    "language_model.model.layers.6.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.6.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.6.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.7.mlp.shared_expert.down_proj",
+    "language_model.model.layers.7.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.7.mlp.shared_expert.up_proj",
+    "language_model.model.layers.7.mlp.shared_expert_gate",
+    "language_model.model.layers.7.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.7.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.7.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.7.self_attn.k_proj",
+    "language_model.model.layers.7.self_attn.o_proj",
+    "language_model.model.layers.7.self_attn.q_proj",
+    "language_model.model.layers.7.self_attn.v_proj",
+    "language_model.model.layers.8.linear_attn.in_proj_a",
+    "language_model.model.layers.8.linear_attn.in_proj_b",
+    "language_model.model.layers.8.linear_attn.in_proj_qkv",
+    "language_model.model.layers.8.linear_attn.in_proj_z",
+    "language_model.model.layers.8.linear_attn.out_proj",
+    "language_model.model.layers.8.mlp.shared_expert.down_proj",
+    "language_model.model.layers.8.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.8.mlp.shared_expert.up_proj",
+    "language_model.model.layers.8.mlp.shared_expert_gate",
+    "language_model.model.layers.8.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.8.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.8.mlp.switch_mlp.up_proj",
+    "language_model.model.layers.9.linear_attn.in_proj_a",
+    "language_model.model.layers.9.linear_attn.in_proj_b",
+    "language_model.model.layers.9.linear_attn.in_proj_qkv",
+    "language_model.model.layers.9.linear_attn.in_proj_z",
+    "language_model.model.layers.9.linear_attn.out_proj",
+    "language_model.model.layers.9.mlp.shared_expert.down_proj",
+    "language_model.model.layers.9.mlp.shared_expert.gate_proj",
+    "language_model.model.layers.9.mlp.shared_expert.up_proj",
+    "language_model.model.layers.9.mlp.shared_expert_gate",
+    "language_model.model.layers.9.mlp.switch_mlp.down_proj",
+    "language_model.model.layers.9.mlp.switch_mlp.gate_proj",
+    "language_model.model.layers.9.mlp.switch_mlp.up_proj",
+    "language_model.mtp.layers.0.mlp.shared_expert.down_proj",
+    "language_model.mtp.layers.0.mlp.shared_expert.gate_proj",
+    "language_model.mtp.layers.0.mlp.shared_expert.up_proj",
+    "language_model.mtp.layers.0.mlp.shared_expert_gate",
+    "language_model.mtp.layers.0.mlp.switch_mlp.down_proj",
+    "language_model.mtp.layers.0.mlp.switch_mlp.gate_proj",
+    "language_model.mtp.layers.0.mlp.switch_mlp.up_proj",
+    "language_model.mtp.layers.0.self_attn.k_proj",
+    "language_model.mtp.layers.0.self_attn.o_proj",
+    "language_model.mtp.layers.0.self_attn.q_proj",
+    "language_model.mtp.layers.0.self_attn.v_proj"
+  ],
+  "missing": [
+    "language_model.lm_head"
+  ],
+  "mismatched": [],
+  "zero_count_experts": 0
+}

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json ADDED Viewed

	@@ -0,0 +1,60 @@

+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
+size 12807982

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,305 @@

+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "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,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|im_end|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+    "extra_special_tokens": {
+        "audio_bos_token": "<|audio_start|>",
+        "audio_eos_token": "<|audio_end|>",
+        "audio_token": "<|audio_pad|>",
+        "image_token": "<|image_pad|>",
+        "video_token": "<|video_pad|>",
+        "vision_bos_token": "<|vision_start|>",
+        "vision_eos_token": "<|vision_end|>"
+    }
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff