Add files using upload-large-folder tool

README.md

@@ -0,0 +1,11 @@
+---
+library_name: mlx
+pipeline_tag: text-generation
+tags: [mlx, hunyuan, hy3, reap, moe-pruning]
+license: apache-2.0
+base_model: tencent/Hy3
+---
+# pipenetwork/Hy3-REAP50-MLX-4bit
+REAP-pruned [tencent/Hy3](https://huggingface.co/tencent/Hy3) (Hunyuan-3): kept **96/192 routed
+experts/layer** by REAP saliency, MLX 4-bit. First REAP-pruned Hy3. Requires mlx-lm hy_v3 (PR #1211):
+`pip install git+https://github.com/kernelpool/mlx-lm.git@add-hy3-preview`

chat_template.jinja

@@ -0,0 +1,222 @@
+{#- ----------‑‑‑ special token variables ‑‑‑---------- -#}
+{%- set HYTK = ':opensource' %}
+{%- set eos_token = '<｜hy_eos{}｜>'.format(HYTK) %}
+{%- set bos_token = '<｜hy_begin_of_sentence{}｜>'.format(HYTK) %}
+{%- set pad_token = '<｜hy_pad{}｜>'.format(HYTK) %}
+{%- set user_token = '<｜hy_User{}｜>'.format(HYTK) %}
+{%- set assistant_token = '<｜hy_Assistant{}｜>'.format(HYTK) %}
+{%- set think_begin_token = '<think{}>'.format(HYTK) %}
+{%- set think_end_token = '</think{}>'.format(HYTK) %}
+{%- set toolcalls_begin_token = '<tool_calls{}>'.format(HYTK) %}
+{%- set toolcalls_end_token = '</tool_calls{}>'.format(HYTK) %}
+{%- set toolcall_begin_token = '<tool_call{}>'.format(HYTK) %}
+{%- set toolcall_end_token = '</tool_call{}>'.format(HYTK) %}
+{%- set toolsep_token = '<tool_sep{}>'.format(HYTK) %}
+{%- set argkey_begin_token = '<arg_key{}>'.format(HYTK) %}
+{%- set argkey_end_token = '</arg_key{}>'.format(HYTK) %}
+{%- set argvalue_begin_token = '<arg_value{}>'.format(HYTK) %}
+{%- set argvalue_end_token = '</arg_value{}>'.format(HYTK) %}
+{%- set toolresponses_begin_token = '<tool_responses{}>'.format(HYTK) %}
+{%- set toolresponses_end_token = '</tool_responses{}>'.format(HYTK) %}
+{%- set toolresponse_begin_token = '<tool_response{}>'.format(HYTK) %}
+{%- set toolresponse_end_token = '</tool_response{}>'.format(HYTK) %}
+{%- set reasoning_mode_token = '<｜reasoning_mode{}｜>'.format(HYTK) %}
+
+{#- ----------‑‑‑ hyperparameters variables ‑‑‑---------- -#}
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- if not preserved_thinking is defined %}
+    {%- if not tools %}
+        {%- set preserved_thinking = false %}
+    {%- else %}
+        {%- set preserved_thinking = true %}
+    {%- endif %}
+{%- endif %}
+{%- if not is_training is defined %}
+    {%- set is_training = false %}
+{%- endif %}
+
+{%- if not reasoning_effort is defined %}
+    {%- set reasoning_effort = 'no_think' %}
+{%- elif reasoning_effort not in ['high', 'low', 'no_think'] %}
+    {%- if reasoning_effort is none %}
+        {{- raise_exception('reasoning_effort error : None, should be no_think/low/high') }}
+    {%- else %}
+        {{- raise_exception('reasoning_effort error : ' + reasoning_effort + ', should be no_think/low/high') }}
+    {%- endif %}
+{%- endif %}
+
+{%- if fallback_strategy is defined and fallback_strategy == 'reasoning_toolcall_retry' %}
+    {%- set reasoning_effort = 'high' %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- if not raw_last_assistant is defined %}
+    {%- set raw_last_assistant = false %}
+{%- 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 is_training %}
+            {%- 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 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 ((preserved_thinking is defined and preserved_thinking) or loop.index0 > ns.last_user_index) %}
+                {%- 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 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 loop.last and raw_last_assistant %}
+                {{- visible_text(message['content']) }}
+            {%- elif 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 +1,692 @@
+{
+  "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,
+  "moe_intermediate_size": 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_router_enable_expert_bias": true,
+  "moe_router_use_sigmoid": true,
+  "num_attention_heads": 64,
+  "num_experts": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "num_shared_experts": 1,
+  "output_router_logits": true,
+  "pad_token_id": 120002,
+  "qk_norm": true,
+  "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,
+  "num_nextn_predict_layers": 1,
+  "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
+    }
+  },
+  "reap": {
+    "kept_per_layer": 96,
+    "orig_experts": 192
+  }
+}

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-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d990954015ba97f0d61eb0257a06e853fad20e0f61782b8114003a00800f0126
+size 5086063650

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f6ae7a2270b276d7dedadf7e3d1db324133ee77d0fd3aaeaf4b6751166cd1d
+size 5363698009

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ef2322e2512b81e3f4223285005228bc09ad6bd049bef817f12dd04d59ad83
+size 5363698184

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e7e7410bd654088be71433aa76de05808b6249fb73d35405fb299f3092cd70
+size 5363698202

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02bb5420fb8bc614cc6c1185b643b7ac1f48117288e2915498ab93b2f0ed038b
+size 5363698080

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f056d4d46d365d88af6cb4a0ce50794e4252d67f75d35439977fe1bbc65ac02f
+size 5363698250

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2eb6f7ae908bf16833787fb3f411e3398e9eae84b092055e2c9cce0e2130f82
+size 5363698230

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2700b2b1f9c20b26cb21a42ae52480fb114a7b6debc102e21038da5c404094cb
+size 5363698106

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0952ebc25b47e9b66b2bb819b07b0b14528dff6a37bad946a672dfacef0337
+size 5363698186

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a615f6928b3f8b51a52b5d90c884679ceeba722e0466ed241fdda81ebefb2a34
+size 5363698162

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fb6f4b48d2fef3fee1a07bf1fe6f077a58be7b0ff6b6c8d42a174198a6a085
+size 5363698176

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b18979b221bdc9857ed10997f8028fe9af43ad86488150e90b2b6a1c5a7d87a
+size 5363698170

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce491ada7aa0d44844520ab0cfd645ebab1ad8dae289092ec02cada36b7b1ba4
+size 5363698256

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f4db6bc8b4ff802cd03e920547f8c701ff556112933eaab4e0aaadedce2f02
+size 5363698246

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9144297247c404d006f554c56c403444c4007a22dad8695e0db6d933b2e310d2
+size 5363698148

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0488c563d28868e99257b026288a0d7f52ad8da564c1f7f57b203c05971a5737
+size 5259895240