Add files using upload-large-folder tool

README.md

@@ -0,0 +1,36 @@
+---
+license: other
+library_name: mlx
+tags:
+- mlx
+base_model: tencent/Hy3-preview
+pipeline_tag: text-generation
+---
+
+# mlx-community/Hy3-preview-4bit
+
+This model [mlx-community/Hy3-preview-4bit](https://huggingface.co/mlx-community/Hy3-preview-4bit) was
+converted to MLX format from [tencent/Hy3-preview](https://huggingface.co/tencent/Hy3-preview)
+using mlx-lm version **0.31.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Hy3-preview-4bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_dict=False,
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,195 @@
+{#- ----------‑‑‑ special token variables ‑‑‑---------- -#}
+{%- set bos_token = '<｜hy_begin▁of▁sentence｜>' %}
+{%- set pad_token = '<｜hy_▁pad▁｜>' %}
+{%- set user_token = '<｜hy_User｜>' %}
+{%- set assistant_token = '<｜hy_Assistant｜>' %}
+{%- set eos_token = '<｜hy_eos｜>' %}
+{%- set think_begin_token = '<think>' %}
+{%- set think_end_token = '</think>' %}
+{%- set toolcalls_begin_token = '<tool_calls>' %}
+{%- set toolcalls_end_token = '</tool_calls>' %}
+{%- set toolcall_begin_token = '<tool_call>' %}
+{%- set toolcall_end_token = '</tool_call>' %}
+{%- set toolsep_token = '<tool_sep>' %}
+{%- set argkey_begin_token = '<arg_key>' %}
+{%- set argkey_end_token = '</arg_key>' %}
+{%- set argvalue_begin_token = '<arg_value>' %}
+{%- set argvalue_end_token = '</arg_value>' %}
+{%- set toolresponses_begin_token = '<tool_responses>' %}
+{%- set toolresponses_end_token = '</tool_responses>' %}
+{%- set toolresponse_begin_token = '<tool_response>' %}
+{%- set toolresponse_end_token = '</tool_response>' %}
+{%- set reasoning_mode_token = '<｜reasoning_mode｜>' %}
+{#- ----------‑‑‑ hyperparameters variables ‑‑‑---------- -#}
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- if not interleaved_thinking is defined %}
+    {%- set interleaved_thinking = false %}
+{%- endif %}
+{%- if not tools %}
+    {%- set interleaved_thinking = false %}
+{%- endif %}
+{%- if not is_training is defined %}
+    {%- set is_training = false %}
+{%- endif %}
+{%- if not reasoning_effort is defined or reasoning_effort not in ['high', 'low', 'no_think'] %}
+    {%- set reasoning_effort = 'no_think' %}
+{%- endif %}
+
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- elif content is none -%}
+        {{- '' }}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- set ns = namespace(last_user_index=-1) %}
+{%- set sp_ns = namespace(system_prompt='', is_first_sp=true) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- set sp_ns.system_prompt = sp_ns.system_prompt + visible_text(message['content']) %}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.last_user_index = loop.index0 %}
+    {%- endif %}
+{%- endfor %}
+{%- if reasoning_effort is defined and reasoning_effort is string and reasoning_effort != '' and not tools %}
+    {%- set sp_ns.system_prompt = sp_ns.system_prompt + reasoning_mode_token + 'reasoning_effort:' + reasoning_effort %}
+{%- endif %}
+{{- bos_token }}
+{{- sp_ns.system_prompt }}
+{%- if tools %}
+    {%- if sp_ns.system_prompt != '' %}
+        {{- '\n\n# Tools\n\nYou may call one or more functions to assist with the user query.' }}
+    {%- else %}
+        {{- '# Tools\n\nYou may call one or more functions to assist with the user query.' }}
+    {%- endif %}
+    {{- '\n\nYou are provided with function signatures within <tools></tools> XML tags:' }}
+    {{- '\n<tools>\n' }}
+    {%- for tool in tools %}
+        {%- if loop.index0 > 0 %}
+            {{- '\n' }}
+        {%- endif %}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- '\n</tools>\n\n' }}
+    {{- 'For function call returns, you should first print ' + toolcalls_begin_token + '\n' }}
+    {{- 'For each function call, you should return object like:\n' }}
+    {{- toolcall_begin_token + '{function-name}' + toolsep_token + '\n' }}
+    {{- argkey_begin_token + '{arg-key-1}' + argkey_end_token + '\n' }}
+    {{- argvalue_begin_token + '{arg-value-1}' + argvalue_end_token + '\n' }}
+    {{- argkey_begin_token + '{arg-key-2}' + argkey_end_token + '\n' }}
+    {{- argvalue_begin_token + '{arg-value-2}' + argvalue_end_token + '\n' }}
+    {{- '...\n' }}
+    {{- toolcall_end_token + '\n' }}
+    {%- if reasoning_effort is defined and reasoning_effort is string and reasoning_effort != '' %}
+        {{- 'At the end of function call returns, you should print ' + toolcalls_end_token + reasoning_mode_token + 'reasoning_effort:' + reasoning_effort }}
+    {%- else %}
+        {{- 'At the end of function call returns, you should print ' + toolcalls_end_token }}
+    {%- endif %}
+{%- endif %}
+
+{%- set prev_ns = namespace(is_tool=false, is_tool_first=true) %}
+{%- set last_ns = namespace(last_is_assistant=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if prev_ns.is_tool %}
+            {{- toolresponses_end_token }}
+        {%- endif %}
+        {{- user_token + visible_text(message['content']) }}
+        {%- set prev_ns.is_tool = false %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' %}
+        {%- if 'reasoning_content' in message and message['reasoning_content'] is string %}
+            {%- set rc = message['reasoning_content'] %}
+        {%- elif 'reasoning' in message and message['reasoning'] is string %}
+            {%- set rc = message['reasoning'] %}
+        {%- else %}
+            {%- set rc = none %}
+        {%- endif %}
+        {%- if is_training %}
+            {%- if rc is not none %}
+                {%- set content = think_begin_token + rc + think_end_token + visible_text(message['content']) %}
+            {%- else %}
+                {%- set content = think_begin_token + think_end_token + visible_text(message['content']) %}
+            {%- endif %}
+        {%- else %}
+            {%- if interleaved_thinking %}
+                {%- if loop.index0 > ns.last_user_index and rc is not none %}
+                    {%- set content = think_begin_token + rc + think_end_token + visible_text(message['content']) %}
+                {%- else %}
+                    {%- set content = think_begin_token + think_end_token + visible_text(message['content']) %}
+                {%- endif %}
+            {%- else %}
+                {%- set content = think_begin_token + think_end_token + visible_text(message['content']) %}
+            {%- endif %}
+        {%- endif %}
+        {%- if prev_ns.is_tool %}
+            {{- toolresponses_end_token }}
+        {%- endif %}
+        {{- assistant_token }}
+        {%- if message['tool_calls'] is defined and message['tool_calls'] %}
+            {%- set prev_ns.is_tool_first = true %}
+            {{- content }}
+            {{- toolcalls_begin_token + '\n' }}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {{- toolcall_begin_token + tool['function']['name'] + toolsep_token + '\n' }}
+                {%- for key, value in arguments.items() %}
+                    {{- argkey_begin_token + key + argkey_end_token + '\n' }}
+                    {%- if value is not string %}
+                        {%- set value = value | tojson(ensure_ascii=False) %}
+                    {%- endif %}
+                    {{- argvalue_begin_token + value + argvalue_end_token + '\n' }}
+                {%- endfor %}
+                {{- toolcall_end_token + '\n' }}
+            {%- endfor %}
+            {{- toolcalls_end_token + eos_token }}
+        {%- else %}
+            {%- if not loop.last or is_training %}
+                {{- content + eos_token }}
+            {%- else %}
+                {{- content }}
+            {%- endif %}
+        {%- endif %}
+        {%- set prev_ns.is_tool = false %}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set prev_ns.is_tool = true %}
+        {%- if prev_ns.is_tool_first %}
+            {{- toolresponses_begin_token + '\n' }}
+            {%- set prev_ns.is_tool_first = false %}
+        {%- endif %}
+        {{- toolresponse_begin_token + '\n' + visible_text(message['content']) + '\n' + toolresponse_end_token + '\n' }}
+    {%- endif %}
+    {%- if loop.last and message['role'] == 'assistant' %}
+        {%- set last_ns.last_is_assistant = true %}
+    {%- endif %}
+
+{%- endfor %}
+{%- if prev_ns.is_tool %}
+    {{- toolresponses_end_token }}
+{%- endif %}
+{%- if add_generation_prompt %}
+    {%- if not last_ns.last_is_assistant %}
+        {%- if reasoning_effort is defined and reasoning_effort in ['low', 'high'] %}
+            {{- assistant_token + think_begin_token }}
+        {%- elif reasoning_effort is defined and reasoning_effort == 'no_think' %}
+            {{- assistant_token + think_begin_token + think_end_token }}
+        {%- else %}
+            {{- assistant_token }}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,688 @@
+{
+    "architectures": [
+        "HYV3ForCausalLM"
+    ],
+    "bos_token_id": 120000,
+    "enable_attention_fp32_softmax": false,
+    "enable_lm_head_fp32": true,
+    "enable_moe_fp32_combine": false,
+    "eod_token_id": 120026,
+    "eos_token_id": 120025,
+    "expert_hidden_dim": 1536,
+    "first_k_dense_replace": 1,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.006,
+    "intermediate_size": 13312,
+    "max_position_embeddings": 262144,
+    "model_type": "hy_v3",
+    "moe_intermediate_size": 1536,
+    "moe_router_enable_expert_bias": true,
+    "moe_router_use_sigmoid": true,
+    "num_attention_heads": 64,
+    "num_experts": 192,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "num_nextn_predict_layers": 1,
+    "num_shared_experts": 1,
+    "output_router_logits": true,
+    "pad_token_id": 120002,
+    "qk_norm": true,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.layers.1.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.38.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.39.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.40.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.41.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.42.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.43.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.44.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.45.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.46.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.47.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.48.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.49.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.50.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.51.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.52.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.53.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.54.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.55.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.56.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.57.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.58.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.59.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.60.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.61.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.62.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.63.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.64.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.65.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.66.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.67.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.68.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.69.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.70.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.71.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.72.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.73.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.74.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.75.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.76.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.77.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.78.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.79.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.layers.1.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.38.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.39.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.40.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.41.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.42.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.43.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.44.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.45.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.46.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.47.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.48.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.49.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.50.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.51.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.52.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.53.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.54.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.55.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.56.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.57.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.58.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.59.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.60.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.61.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.62.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.63.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.64.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.65.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.66.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.67.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.68.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.69.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.70.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.71.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.72.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.73.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.74.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.75.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.76.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.77.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.78.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.79.mlp.router.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+        "rope_theta": 11158840.0,
+        "rope_type": "default"
+    },
+    "route_norm": true,
+    "router_scaling_factor": 2.826,
+    "sep_token_id": 120007,
+    "tie_word_embeddings": false,
+    "transformers_version": "5.6.0",
+    "use_cache": true,
+    "use_grouped_mm": false,
+    "vocab_size": 120832
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+    "bos_token_id": 120000,
+    "do_sample": true,
+    "eos_token_id": 120025,
+    "pad_token_id": 120002,
+    "temperature": 0.9,
+    "top_k": -1,
+    "top_p": 1,
+    "transformers_version": "5.6.0"
+}

model-00001-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3cdf1fc52c99ca762739a40bdad9f4fc80a07a329c9f9933bc527f1284284a7
+size 5319591251

model-00002-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d586afc124446c37e4c7fe8b3bdc93be71f897df00601724bd6a5042e4b13d2
+size 4864224955

model-00003-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2cd7a70e59c475de61404e50468267613877ad69787548125eba43667d53a7
+size 4918165689

model-00004-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7c9ab0944202f19a9a74691a673de0f8c2753bb33e294fc127c4bd9ec654c2
+size 4864224960

model-00005-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcee8de10f7718388551c783e7ad4c89ff4d9fe622c21f00e5cae604231acf7
+size 4864225040

model-00006-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2df009d84fd2e17d2c2ec2b01b7d821b557a59232ac24f4f4cbe7485586eaa
+size 4918165735

model-00007-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c43df9f1d7d72874b73e779def5c732376c0278476cb70b4092d97b3aa2bbc5
+size 4864224956

model-00008-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfabaff58aea50089b3f383ae77a38fed049e9ada0933212cec6b7f718045e0d
+size 4864225074

model-00009-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed23b3cd6f679e3ca5c904e31b13abc8235a19061f1a75c54c7d8e3f2ef62ea7
+size 4918165767

model-00010-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dedeeec81e53c3f3851044024ae6ccd1121a54675a0c1eb9101ff3cacba1e41b
+size 4864224972

model-00011-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004e03a4a2f0c23628708ddd812ad21055300aa6014f5819674bda8b9ad87502
+size 4864225022

model-00012-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840cb1ebafcd0eb20f240346cd588c55ba0c600349935742f710615ab4a9e6ce
+size 4918165825

model-00013-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be83d61db071d933a6bd7bb25b9d3f75c456e78200e9a774d1d72fb5db7e4682
+size 4864225016

model-00014-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1755fb4ad8e951eea9b3e59ed973d7e78044155010aa22ca132b1d5806e992
+size 4864225000

model-00015-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dab91860d804497cc4af970b2beb4eb1c0c4f4750585f477c8a586ba64e0d6
+size 4918165779

model-00016-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24407218c575f257f9be3c0090888239d93e12ad14a12bc3dbf18f0966dc90cd
+size 4864225006

model-00017-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d7e24cdccf05c401256d3ae89b10854a73a39bd81f455307439f0b6e6ff5fc
+size 4864225042

model-00018-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6038a0a4501e41bcc4814860107cd5c46fcc89b7d934a396205aff72ebf957c7
+size 4918165767

model-00019-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787bf8c5455cf94ae002c6a17a7d8117ee18ff07e5f67081eb3ce9a7f37016fd
+size 4864224990

model-00020-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad9a1a94f5efb9c749e1df367f2541a6b61f4dc0b168c7f36b33ef1808e34f3
+size 4864225000

model-00021-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2839beab09cb2a68b22ce6cfe7ed9ec1efb87660c91e99602368ad763918c8
+size 4918165807

model-00022-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467c8ffaaef5171c1dafda160eaa5829608569422cbb9e78413e0095fa4040ad
+size 4864225044

model-00023-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc6265db462d41c719bf56830e9a5c369d24c7d99d6e5c41d44b9c95673390a
+size 4864225034

model-00024-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c205270c049bf31fda52d51e2f669e5fc3da466d4fe7548084768e92c5fd2e
+size 4918165781

model-00025-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32578d17cb599c1853d1e3301da7fde75e5c7cd043be48250c8b9cd2ec99c76e
+size 4864225022

model-00026-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6868c14bcde362f17c9be5ae8817e3603da7da6dd8921e514ddcba31c47b1759
+size 4864225082

model-00027-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509d647b23611c2090a8c2d68c4877f06135785f0e09f506d076cb33dd0be0dd
+size 4918165785

model-00028-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac7c5d16fd88bfdc27ac487665872082c8d2816618c379c2734d70bb22c341e
+size 4864225046

model-00029-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4b69590c19a5c21c59fd4472fd9f62000e8d831de5aac2afefe5086d2a892c
+size 4864225076

model-00030-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a75c759fcf65881aada483183223aad979964f5e69efef84da7add01c921b7b
+size 4918165811

model-00031-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf8e4aab4b0c6f76baa533c9386cf33950f1737c3f0d181d63f97bf1e25a6e1
+size 4864225050

model-00032-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd6e8f3ac93eace8e32b60cdb405398d4a2d2d5a61e356d32f8c149b1138080
+size 4864225032

model-00033-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaacd187f4e2db10328093ffddedd791bb068d1ede22f614efe8aef0659e320a
+size 4918165797

model-00034-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1341217be54b7b5ccb885ad5e45f0faa692cb526a41cb46b5ea5f4bf4c3420b
+size 4420683411

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜hy_begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜hy_eos｜>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<｜hy_▁pad▁｜>",
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "hy_v3"
+}