Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ 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
+train_vs_eval_loss.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,147 @@
+---
+language:
+- en
+library_name: mlx
+pipeline_tag: text-generation
+license: apache-2.0
+base_model: Qwen/Qwen3.6-35B-A3B
+base_model_relation: quantized
+datasets:
+- aisamdasu/algocean-fable5-traces
+tags:
+- mlx
+- optiq
+- quantized
+- mixed-precision
+- qwen3.6
+- qwen3.5-moe
+- lora
+- sft
+- tool-use
+- agentic
+- langgraph
+- fable5
+---
+
+# Algocean-Qwen3.6-35B-A3B-mlx-OptiQ
+
+Quality-first OptiQ MLX release of the Algocean fine-tune derived from `Qwen/Qwen3.6-35B-A3B`.
+
+The source model for this quantized release is `aisamdasu/Algocean-Qwen3.6-35B-A3B-mlx`, which was produced by merging the best LoRA checkpoint from the Algocean SFT run. This artifact keeps the same text-focused MLX scope as the merged MLX release: the current `mlx-lm` Qwen3.5-MoE conversion stores language-model weights and omits `model.visual`.
+
+## Use
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("aisamdasu/Algocean-Qwen3.6-35B-A3B-mlx-OptiQ")
+
+messages = [{"role": "user", "content": "Create a concise LangGraph plan for a repo refactor."}]
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+response = generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True)
+```
+
+## Artifact
+
+| item | value |
+|---|---:|
+| Format | MLX safetensors |
+| Quantization | OptiQ mixed precision |
+| Shards | 7 |
+| Weight size in MLX index | 36,036,335,872 bytes |
+| Parameters in MLX index | 34,660,608,768 |
+| Converter output size | 34,367.2 MB |
+| Visual weights | omitted |
+| Integrity file | `SHA256SUMS` |
+
+## OptiQ Settings
+
+| key | value |
+|---|---|
+| Method | `optiq_mixed_precision` |
+| Source artifact | `aisamdasu/Algocean-Qwen3.6-35B-A3B-mlx` |
+| Target BPW | 4.5 |
+| Achieved BPW | 4.733167 |
+| Candidate bits | 4, 8 |
+| Allocation | 297 tensors at 4-bit, 94 tensors at 8-bit |
+| Reference | `uniform_4bit` |
+| Group size | 64 |
+| Calibration source | `aisamdasu/algocean-fable5-traces` train split |
+| Calibration mix | 512 train records sampled before eval separation |
+| Exact calibration | 24 samples, 48 calibration sequences, seq_len 512 |
+| Evaluated tensors | 391 |
+| Skipped sensitivity entries | 120 entries without BF16 source match |
+
+This is the quality-first OptiQ export from this run. Instead of publishing a smaller static or uniform 4-bit artifact, the exact OptiQ pass measured layer sensitivity on the FABLE/LangGraph calibration mix and kept the more sensitive tensors at 8-bit. The result is larger than a uniform 4-bit model, but preserves more capacity in the layers that measured as most sensitive for this calibration workload.
+
+## Training
+
+| key | value |
+|---|---|
+| Base model | `Qwen/Qwen3.6-35B-A3B` |
+| Dataset | `aisamdasu/algocean-fable5-traces` |
+| Train / eval rows | 30,265 / 512 |
+| Selected source rows | Crownelius 26,938 + kelexine 3,839 |
+| Dedup skipped | 1,721 |
+| Fine-tune method | LoRA SFT |
+| LoRA target modules | `q_proj`, `v_proj` |
+| LoRA rank / alpha / dropout | 16 / 32 / 0.0 |
+| Max sequence length | 16,384 |
+| Optimizer / schedule | AdamW fused / cosine |
+| Learning rate / warmup | 1e-5 / 0.03 |
+| Batch / grad accumulation | 1 / 1 |
+| Max steps | 4,000 |
+| Eval / save interval | 200 / 200 |
+| GPU | Modal B200 x1 |
+| Runtime | 7,934.71 sec |
+
+## Checkpoint Selection
+
+The published weights use checkpoint `3600`, not the final step `4000`.
+
+| step | eval loss | eval PPL | note |
+|---:|---:|---:|---|
+| 200 | 1.300712 | 3.671911 | first eval |
+| 3200 | 1.067631 | 2.908480 | near plateau |
+| 3400 | 1.067996 | 2.909543 | regression |
+| 3600 | 1.066911 | 2.906388 | selected best |
+| 3800 | 1.067495 | 2.908084 | worse than best |
+| 4000 | 1.067005 | 2.906661 | final, slightly worse |
+
+Best checkpoint rationale:
+
+- `3600` has the lowest validation loss: `1.066911`.
+- Final step `4000` is very close but still higher: `+0.000094` eval loss.
+- The curve flattened after `3200`, so selecting `3600` keeps the best validation point without chasing extra train loss.
+
+![Eval loss vs step](./eval_loss_vs_step.png)
+
+![Train vs eval loss](./train_vs_eval_loss.png)
+
+![Learning rate vs step](./learning_rate_vs_step.png)
+
+## Metrics
+
+| metric | value |
+|---|---:|
+| Best eval loss | 1.066911 |
+| Best eval perplexity | 2.906388 |
+| Final eval loss | 1.067005 |
+| Final eval perplexity | 2.906661 |
+| Trainer average train loss | 0.494604 |
+| Last logged train loss | 0.996137 |
+| Train samples/sec | 0.504 |
+| Train steps/sec | 0.504 |
+| Eval samples/sec at final eval | 2.088 |
+
+## Comparison Notes
+
+This OptiQ artifact is selected for fidelity under the available local export options: best validation checkpoint first, then exact OptiQ sensitivity allocation instead of static quantization. It is not claiming a public benchmark win over the base model, the merged MLX model, or the upstream OptiQ model; that would require the same held-out benchmark harness across all models. The comparison recorded here is based on the completed training run's validation curve and the OptiQ allocation metadata.
+
+## Intended Use
+
+This model is intended for local MLX inference experiments around agentic coding, tool-use traces, and LangGraph-style planning. It is not a general safety-tuned assistant release.

SHA256SUMS

@@ -0,0 +1,19 @@
+8972d7bbabf98b57e3cc9a38d1e08d5e363ef8fa790aec20be1effcce04ef950  ./README.md
+e84f32a23fdda27689f868aa4a1a5621f41133e51a48d7f3efcbea2839574259  ./chat_template.jinja
+a00add6509456b79aae20eb36adf7ed1489344d6d80c0f644b079dab366c2eb7  ./config.json
+64e9c3af45c8aaa13f81bd76fa53b15908185ddbf9c98012535385a938a4ffc0  ./eval_loss_vs_step.png
+e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e  ./generation_config.json
+4dfeec7796c7ffeaf9d0b552be5047e150022710c674b6fc00cd6f75238116d1  ./learning_rate_vs_step.png
+d779c13b4d9035dd0add832e5e67490762193e41548ca6a44b072a9b5be740ce  ./metrics_summary.json
+25ad04d6cab1dfb2892cd6451ff28d2b6e47d33b0258dd3d8819c46a868e4b66  ./model-00001-of-00007.safetensors
+0e4550d4b3bc2faa46d6e293adf2cb9b690e3e59cbd6e32eee47f1efecd73ca2  ./model-00002-of-00007.safetensors
+eeeec3492d95e10147707288aa2bae98ca7a1abdfbd2f214d928a631efe60019  ./model-00003-of-00007.safetensors
+aace929e8abfdeda83d11f22c9dc621325545d7c9bf7ec78eb85bc8aaac1feb3  ./model-00004-of-00007.safetensors
+69ab88237419cea727f33a5331f1ce79f28e4e1e4abfba5b716636e9465f7b4d  ./model-00005-of-00007.safetensors
+e2c997337eda31eadc075a97e6980f954b5be3bca13a273744b2bb8ef4897eaa  ./model-00006-of-00007.safetensors
+36c71aae629e57071c01c7baffff40ddf6a8d10c7edbca8f089fbb909ee69f06  ./model-00007-of-00007.safetensors
+672102b0a89e7321f9aa735047095d82d5fc16189a4ef15e5434ebeb8885e9f6  ./model.safetensors.index.json
+be8ef60f68450a8bef4705b5130879a09511872f411bd44177b3418ad30141d5  ./optiq_metadata.json
+06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523  ./tokenizer.json
+95c557768e6b88a7128befc7bfd3c7de50e5d51af9b8b33a9f4dee0e04f99679  ./tokenizer_config.json
+772d3b5bf3ae3f3da8729678c9b3b368ca89f214ae92f1fbbf38ae7c8072b1d9  ./train_vs_eval_loss.png

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
+}

metrics_summary.json

@@ -0,0 +1,12 @@
+{
+  "best_step": 3600,
+  "best_eval_loss": 1.066911220550537,
+  "best_eval_ppl": 2.9063884285567174,
+  "final_train_loss": 0.9961370468139649,
+  "final_eval_loss": 1.0670050382614136,
+  "final_eval_ppl": 2.906661112057073,
+  "final_train_eval_gap": 0.07086799144744871,
+  "trainer_best_checkpoint": "/adapters/mythos_v1_q36_35ba3b/checkpoint-3600",
+  "trainer_best_metric": 1.066911220550537,
+  "global_step": 4000
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ad04d6cab1dfb2892cd6451ff28d2b6e47d33b0258dd3d8819c46a868e4b66
+size 5251236990

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4550d4b3bc2faa46d6e293adf2cb9b690e3e59cbd6e32eee47f1efecd73ca2
+size 5279904037

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeeec3492d95e10147707288aa2bae98ca7a1abdfbd2f214d928a631efe60019
+size 5283090938

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aace929e8abfdeda83d11f22c9dc621325545d7c9bf7ec78eb85bc8aaac1feb3
+size 5279904222

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ab88237419cea727f33a5331f1ce79f28e4e1e4abfba5b716636e9465f7b4d
+size 5283090926

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c997337eda31eadc075a97e6980f954b5be3bca13a273744b2bb8ef4897eaa
+size 5279904224

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c71aae629e57071c01c7baffff40ddf6a8d10c7edbca8f089fbb909ee69f06
+size 4379440822

optiq_metadata.json

@@ -0,0 +1,1576 @@
+{
+  "method": "optiq_mixed_precision",
+  "base_model": "artifacts/Algocean-Qwen3.6-35B-A3B-mlx",
+  "reference": "uniform_4bit",
+  "target_bpw": 4.5,
+  "achieved_bpw": 4.733167124445384,
+  "n_high_bits": 94,
+  "n_low_bits": 297,
+  "threshold": 0.0,
+  "per_layer": {
+    "language_model.lm_head": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.39.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.38.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.37.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.36.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.35.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.34.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.33.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.32.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.31.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.29.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.28.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.27.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.26.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.25.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.24.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.23.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.19.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.15.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.14.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.13.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.11.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.10.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.7.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.4.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.mlp.shared_expert.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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.3.self_attn.q_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.mlp.gate": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.1.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert_gate": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert.up_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert.down_proj": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.mlp.shared_expert.gate_proj": {
+      "bits": 4,
+      "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": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.linear_attn.in_proj_z": {
+      "bits": 4,
+      "group_size": 64
+    },
+    "language_model.model.layers.0.linear_attn.in_proj_qkv": {
+      "bits": 4,
+      "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|>"
+}