Add files using upload-large-folder tool

README.md

@@ -0,0 +1,36 @@
+---
+license: other
+library_name: mlx
+base_model: tencent/Hy3-preview
+pipeline_tag: text-generation
+tags:
+- mlx
+---
+
+# mlx-community/Hy3-preview-8bit
+
+This model [mlx-community/Hy3-preview-8bit](https://huggingface.co/mlx-community/Hy3-preview-8bit) 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-8bit")
+
+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": 8,
+        "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": 8,
+        "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-00002-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aaaa02197d2b91ad7493712fadbb6cf6678780845ecc0f2fa08b9df6233be8a
+size 5234956298

model-00003-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8ced0f2e5087e9f3781b60a1954a80faa5c356ec11d65e19f55624dd8f84b9
+size 5234956346

model-00005-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc097d528aaa18e21b26978010f4465ac51e3001be30f34b45d9baa327b80cc
+size 5234956368

model-00006-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6005b9f15d984891eda5c0cd463edfeb25ffe251340263dd26e03d49167c1d1
+size 5234956358

model-00007-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9a0272b65e196bebe7fe804733bb877bdf0f8a19574320e0990d6bfb73f086
+size 5336082996

model-00008-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb2656e68d203fa2c38ca9ccd16fead15dc89013c411f14031a1e114a4ebc6f
+size 5234956401

model-00009-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d939348b7ceeb6b95429a4f204afb3a2ac5581c33a410928774a58644d8ee0
+size 5234956399

model-00010-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744163aba96a4da47d73d622f3ece05dcec2e07f1f56d9267c34636374177cf7
+size 5336083044

model-00011-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70e6802f74f9549ea5ce98c98d67a7d55269ae19a71b83a633311a841b23cf6
+size 5234956401

model-00012-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8195850e621a6f3b42f330863af64e1b56a6b2186509d1235a2da909dcfb8b87
+size 5234956399

model-00014-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9d43e6379c5720283bfbc47eb09752a92e46acc6cee0ba5a0a446af7e775eb
+size 5234956371

model-00015-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4655bfc91b2abe5af06d5a6367670fa45db0ab359bea874719e2130f54ef22
+size 5234956403

model-00017-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85958d1814ac62f65f4979b00d3f8f4ecd9f1de03858dae4de533fa067c9c22
+size 5234956319

model-00018-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5282622607f7077156fe8e58232f95b7eb664b01af4a0cda515e791f5933237
+size 5234956395

model-00020-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69386ddc2c2aee378fbc5e88f8f0ca20bef236eab0420023cf8fc888f344695e
+size 5234956367

model-00023-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2128241a7bff76a4580533d329ec903bfc91551780b6fa09bd614097aeeac1a5
+size 5234956405

model-00025-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad45ba4b53bb089f9b02f97dc2d64abd08161e4e16e138dd0e54c2503e0a1214
+size 5336083078

model-00026-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f86540c156071c6d079c7fdd1632fdec2555161b54dae8dd326b9f682b43d23
+size 5234956393

model-00028-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36a03cc5e668cb8f4944b4c2e48e27b65f4847c9dce5151c5abde6c88c0b4a0
+size 5336083066

model-00029-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754701bf34f993007865c8908a987a58dd4dbfa111f9b8a704abb0efa9cc8986
+size 5234956341

model-00030-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba60d9fbcbdae819fcf5f0bfd486dd97e251c0527a83401ffa0e01842b117267
+size 5234956399

model-00031-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be6ed4812c5f3de3038df10ea74409dd77f0171553ca7a604fa6008bc4c4ec0
+size 5336083060

model-00032-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8327780db94cb5eb0ca5ea5835cd7027510ba2e9c3775f01679c2c73e125e2a3
+size 5234956305

model-00034-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afc97529b7774bba0b247ab2dd6fa8bc9b92f50ccfb4002b2b7f2013e11cf3a
+size 5336083054

model-00035-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3abee770f67ecc6850f9a0fa6b0f9aa73e78b460b771ef3e96681c6f2196d0b
+size 5234956393

model-00037-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080e491b5ae5f410a594dab6de479263019fe6e1427eb83ba6f7d800f8f27366
+size 5336083098

model-00038-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09666ab09950af639bc0e58a0ab3d317cca30f252717eb2b19a5d671619dcbad
+size 5234956405

model-00039-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf31cd7aaf73d3c325815a4bc467ee42210f698b454485f34d7ec95d66339a6
+size 5234956379

model-00040-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b786f81926c80a849dafcbdb1884076eb0bd6b39c89e923c5c2d0ac992707c45
+size 5336083054

model-00041-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4c22bc6d7f8f8cd222fabd87f1add1d66ed1465fc7f651af4b71899d975f57
+size 5234956367

model-00042-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bdaab644e462007eba221eaaf80dd7a81641122671b5efa8527e83209b2faae
+size 5234956399

model-00043-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a6734d9d5da934f1b041f4631d31c6ffa87d6ca7ee3dfff60425295a09d000
+size 5336083038

model-00044-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d95c3df64c9e9413b6562bea0094a64603fda6c64fa5722e06423a1da5c1fe3
+size 5234956371

model-00046-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38a48da9dc29f7ee827a9c9b832cb45b0827eee9d12604138abce251fc312ad
+size 5336083058

model-00047-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10da543ff40df600e85ad3db5c4530c969514b8bca231c7b4ccacb4fed4dc90
+size 5234956401

model-00048-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1817fb0fceb5d99fd5c37288e63d712295f1f122b09d476c11e2c345b49f346
+size 5234956395

model-00049-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795a04aa1f43095dbdc78140666746ffa254f9cf3ee4793007ddf8826a0d3705
+size 5336083076

model-00050-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c9cd3881d65a6961e3e1bb6590ce1418a268edafa6778d00d4342746a1addc
+size 5234956401

model-00051-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615407916d170a03b5e1e3f6e2810e499ac96dca206a49fc6ae8f1961a90e4c4
+size 5234956399

model-00053-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1019f64cdbd149af79f7a34a25c45dfeb9741e25b56e7ba22f09a2eaf23443c3
+size 5234956401

model-00054-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f438c440bb6357dde55ad467dd2ba6b5e753bc753d25a69281accd854bc72471
+size 5234956403

model-00055-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea557f5433f5b01420f0c174b947b1b5af4d37051833be7045836a4efe31af4
+size 5336083078

model-00059-of-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ad5e65dba229ba68a390fae25ae7ffdae4991e1337ac227fa8cbcfb6f251b2
+size 5234956401

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"
+}