Add files using upload-large-folder tool

README.md

@@ -0,0 +1,36 @@
+---
+license: other
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+- mlx
+base_model: tencent/Hy3-preview
+---
+
+# mlx-community/Hy3-preview-6bit
+
+This model [mlx-community/Hy3-preview-6bit](https://huggingface.co/mlx-community/Hy3-preview-6bit) 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-6bit")
+
+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": 6,
+        "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": 6,
+        "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-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a3f771f8a6e1a4475c31b4dc09ccf86b11dbf7dbd41ba9203d2d64c0fb34df
+size 4661145304

model-00002-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e9a80d0b353f2ab4aa4240779be2e00e3f008c92209a00e0a16b80a572579b
+size 5062405029

model-00003-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60dfeffea988c883b84766531013aba0fd01fa58fd26036f9943723a4dda58e4
+size 4984871347

model-00004-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce140fa5fb9dc918f915b60f123d4be6a570073c4f4454261157918b47bce68
+size 5062405055

model-00005-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b487f25a3e1cf8b819c29b1d9272a2b2e2ad5a84c9557d7e25308d031e0239e
+size 5062405021

model-00006-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c3c4afab0293982e7373322ce04678330723c223c969988a0ca9e1a3679ff3
+size 4984871367

model-00007-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378c489fc46beb44bfaabdc661acbb728695b9e0d00d946ad686e7107318b319
+size 5062405126

model-00008-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11e63ce55c58607cd35376618327a4660091871877e725fac3e5c472f20f4d6
+size 5062405062

model-00009-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ac0fa4561df8e3e0cd1a66a74ab3f994b322896f1a65be1ba926ea9e185c85
+size 4984871379

model-00010-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920f46d601dd3df0aaaecdddf2543ce1c6b5f71f7cab4aab3c041de21840bff2
+size 5062405146

model-00011-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2eeaf6597ce05456cd1041d855aac792856c4521a705b3622a645dc6aae574
+size 5062405050

model-00012-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb7a997d06b957fd5f6dcd08eef2af3719787d05e782cc5d3601562c40001d9
+size 4984871397

model-00013-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c502931ee29377a555f41a4d906e5184c911244a24d724d20cbee5a3a84f2010
+size 5062405132

model-00014-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:930d129a43a12f53394b0b66da8cb74818ef975aa8e2f61161fbe54a6e43a35e
+size 5062405072

model-00015-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5260a7bfaea3dfc531d3334ff41b64265b4c317da5b4ef7bf04bfa5442b8de2e
+size 4984871395

model-00016-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3022d2a47bd68acf30200a167c13edaf779c59f045b9214e42ac7a0a05838e
+size 5062405148

model-00017-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c193345ca0c7e8af6b3509c426de5ea4dac4bf511691043d7001a2f99edfe484
+size 5062405116

model-00018-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff45ca068ac95c3fa158cd1c5671086a8d24025e36a0fda701107112213e9528
+size 4984871349

model-00020-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e4a9a6f726bd811b629961e94108d265f4920d6928ee1fae355adb676f0149
+size 5062405108

model-00021-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b354b7f324ff82d44897e8601c0c1c05ca745e4cce3be4d8a7e05c414ccf49
+size 4984871391

model-00022-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979fd5feda8147b79002a0ab02ba7973bb457ac907e61ff863104e8e689dc08f
+size 5062405178

model-00023-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130852b3bcf3c1e7eb08211ce3039e4ec57f07fe99ce1a58a85f54f06096aff4
+size 5062405072

model-00026-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe1ad000ed5365b6cd91bd37ed707df024c546a4ec1a40a48031dc657fa2a46
+size 5062405100

model-00027-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34810cbba394379ef0030e003409ca6c7424cc57e03eaf27cec5a2f4a59970f
+size 4984871375

model-00028-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b5ad2b43c3acd24325a072f7175237d6eb94f9a5f4cfd0698187bba28b05fb
+size 5062405088

model-00029-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2890dc24343ea418e83fcbdc33e7c56442e61771a5270800d418a7fd79c4a9ff
+size 5062405106

model-00030-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a030fe22adcb1d52e8930c54e3ac64a611aa20600d69d2ff1af3cf9cf268fd5
+size 4984871393

model-00031-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16800c689012aba6fce040955f531dc8b782f6ab9df8aca91c1beb3019fd7d8
+size 5062405160

model-00032-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c7f31af6b912d3b3431a06089db42cc3f871b54b1f432c318ec2100b8ddcfe
+size 5062405070

model-00033-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859329d92b68e5760546d7009b8267b95e687ef80eb7d65126c8c874f5cd3cbe
+size 4984871393

model-00034-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78863853796cffcad0de010f7db63121d85301c080e9fa24b971c70dcd4a470
+size 5062405148

model-00035-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed0f1eeee2043e3ad579fce48baabea2a79d1a705db824718ae4801b998de028
+size 5062405064

model-00036-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d71b99d5baea2c75ce516ce53d1fa43f6fe7bc0d3b45900e297b9efca58622d
+size 4984871395

model-00039-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d945ebe940a4c1a9d9f11e94cced8e80956470b5e3d8583ce8772bf60e9ccdf9
+size 4984871377

model-00040-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd44751a3cb1d39e595b6783b31425db8772237a1dc5da346e04dfff30b92a7
+size 5062405158

model-00041-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:472f212be22480b89531eb8733c594d38f6f5360048359e092670cbcd88494dc
+size 5062405060

model-00042-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837c83c332bfa171d8290f9bfd9044ca6962b69af33b65eb7d4c239e2df9c98e
+size 4984871349

model-00043-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8323916cb122c29d9127401ca03fe55ec008868a5cfcb710d8c00dfba2a79ea9
+size 5062405144

model-00044-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4030cdbd12a30fe462148ad9e9cd176f516859db7d25f5ab2554874b3a0cb188
+size 5062405096

model-00045-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa7bd314717e436640365aa4603f65d58bae0d1e4dc38d956aed4792611a486
+size 4984871375

model-00046-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3443598d3ac1559a3c60b29ecc0ea05a12af7c9c7614854c886208cc2e96d8e
+size 5062405160

model-00047-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30f4b76cb6fe925543b3dba291683c931824b31efbb1e695392b7c594e550c2
+size 5062405106

model-00048-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b569314f8b5cbcb9f4b47b389e8f6befd37ff42e82b94a161967213f9dbc16
+size 3362729986

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"
+}