Add files using upload-large-folder tool

.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

@@ -0,0 +1,46 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- mlx
+- optiq
+- code
+library_name: mlx
+pipeline_tag: text-generation
+base_model: Kwaipilot/KAT-Coder-V2.5-Dev
+---
+
+# KAT-Coder-V2.5-Dev-OptiQ-4bit
+
+> **Built with [mlx-optiq](https://mlx-optiq.com)**, the MLX-native toolkit to
+> quantize, fine-tune, and serve LLMs locally on Apple Silicon (no PyTorch, no
+> cloud). [Try the Lab](https://mlx-optiq.com/docs/lab/) · [All OptiQ
+> quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/)
+
+An [OptiQ](https://mlx-optiq.com) mixed-precision MLX quant of
+**KAT-Coder-V2.5-Dev**, a `qwen3_5_moe` coding model (256-routed-expert sparse
+MoE with hybrid linear + full attention).
+
+- **Mixed 4/8-bit `static` build** — per-layer bit-widths assigned to a 4.5
+  target bits-per-weight: 400 projections at 4-bit, 111 at 8-bit.
+- **~4.51 bits per weight**, 20 GB on disk.
+
+## Requirements
+
+```bash
+pip install -U optiq
+```
+
+`qwen3_5_moe` loads under stock `mlx-lm` too, but `optiq serve` adds mixed-
+precision loading, KV-cache quantization, and the OptiQ Lab.
+
+## Running it
+
+```bash
+optiq serve --model mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit
+```
+
+Then use the OpenAI-compatible endpoint at `http://localhost:8000/v1`, the
+[OptiQ Lab](https://mlx-optiq.com/docs/lab/), or point `optiq code` at it. This
+is a reasoning coder — it thinks before it answers.

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- 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 %}
+        {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- 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 %}

generation_config.json

@@ -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
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b8ab10f7c280f408086ed9a97ce9adfb147ca484f2e963d3773a508e61f5a4
+size 5310356153

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b42106ea428c947a34379e81a2f51fcb2454b7e945f4a0f60c785521589cd2
+size 5367895955

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac181b1330eb97a3550854b957f1a651b61ceda7bdd6ad4c726455311855d32f
+size 5247553401

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2b85371b711a8227fe314850b7c7d4efad1cd2b610d64facf3747a1365f93c
+size 5175341284

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a55d7784c46d7e3deaf7fbf1ea4bdfa814f5dae22e40c0379c7c5114a2a34ab
+size 828908082

optiq_metadata.json

@@ -0,0 +1,2056 @@
+{
+  "method": "static_mixed_precision",
+  "base_model": "/Users/codelion/.cache/huggingface/hub/models--Kwaipilot--KAT-Coder-V2.5-Dev/snapshots/7a4a45dc6426b4951be99a9f230557c0b0b77761/",
+  "reference": "structural_rules",
+  "target_bpw": 4.5,
+  "achieved_bpw": 4.510037156886497,
+  "n_high_bits": 400,
+  "n_low_bits": 111,
+  "threshold": 0.0,
+  "per_layer": {
+    "language_model.lm_head": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.switch_mlp.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.switch_mlp.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.switch_mlp.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.switch_mlp.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.switch_mlp.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.switch_mlp.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.switch_mlp.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.switch_mlp.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.switch_mlp.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert_gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.switch_mlp.down_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.switch_mlp.up_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.switch_mlp.gate_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.gate": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.linear_attn.out_proj": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.linear_attn.in_proj_z": {
+      "bits": 8,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.linear_attn.in_proj_qkv": {
+      "bits": 8,
+      "group_size": 64
+    }
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_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|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "tool_parser_type": "qwen3_coder",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}