Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,257 @@
+[gMASK]<sop>
+{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}
+{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
+{%- set clear_thinking = clear_thinking if clear_thinking is defined else false -%}
+{%- if tools -%}
+{%- macro tool_to_json(tool) -%}
+    {%- set ns_tool = namespace(first=true) -%}
+    {{ '{' -}}
+    {%- for k, v in tool.items() -%}
+        {%- if k != 'defer_loading' and k != 'strict' -%}
+            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
+            {%- set ns_tool.first = false -%}
+            "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- endmacro -%}
+{%- macro tool_references_to_response(refs) -%}
+    {{- '<tool_response><tools>\n' -}}
+    {%- for tr in refs -%}
+        {%- for tool in tools -%}
+            {%- if 'function' in tool -%}
+                {%- set tool = tool['function'] -%}
+            {%- endif -%}
+            {%- if tool.name == tr.name -%}
+                {{- tool_to_json(tool) + '\n' -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endfor -%}
+    {{- '</tools></tool_response>' -}}
+{%- endmacro -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{%- if 'function' in tool -%}
+    {%- set tool = tool['function'] -%}
+{%- endif -%}
+{% if tool.defer_loading is not defined or not tool.defer_loading %}
+{{ tool_to_json(tool) }}
+{% endif %}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
+{%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%}
+{%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%}
+{%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- endmacro -%}
+{%- 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 -}}
+            {%- elif item is mapping and item.type in ['image', 'image_url'] -%}
+                {{- emit_image() -}}
+            {%- elif item is mapping and item.type in ['video', 'video_url'] -%}
+                {{- emit_video() -}}
+            {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}
+                {{- emit_audio() -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro tool_response(text) -%}
+{{- '<tool_response>' + text + '</tool_response>' -}}
+{%- endmacro -%}
+{%- macro render_tool_response(m) -%}
+{%- if m.content is string -%}
+    {{- tool_response(m.content) -}}
+{%- elif m.content and m.content is not mapping and m.content.0.type == "tool_reference" -%}
+    {{- tool_references_to_response(m.content) -}}
+{%- elif is_list_of_outputs(m) -%}
+    {%- for tr in m.content -%}
+        {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == "tool_reference" -%}
+            {{- tool_references_to_response(tr.output) -}}
+        {%- else -%}
+            {{- tool_response(visible_text(tr.output)) -}}
+        {%- endif -%}
+    {%- endfor -%}
+{%- else -%}
+    {{- tool_response(visible_text(m.content)) -}}
+{%- endif -%}
+{%- endmacro -%}
+{%- macro id_of(obj) -%}
+    {%- if obj.tool_call_id -%}
+        {{- obj.tool_call_id -}}
+    {%- elif obj.id -%}
+        {{- obj.id -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- macro is_list_of_outputs(m) -%}
+    {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro has_dup_tool_result_id(lo, hi, target) -%}
+    {%- set ns_cnt = namespace(n=0) -%}
+    {%- for k in range(lo, hi + 1) -%}
+        {%- set m = messages[k] -%}
+        {%- if is_list_of_outputs(m) -%}
+            {%- for entry in m.content -%}
+                {%- if id_of(entry) == target -%}
+                    {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- elif id_of(m) == target -%}
+            {%- set ns_cnt.n = ns_cnt.n + 1 -%}
+        {%- endif -%}
+        {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}
+    {%- endfor -%}
+    {%- if ns_cnt.n > 1 -%}1{%- endif -%}
+{%- endmacro -%}
+{%- macro tc_id_exists(tcs, target) -%}
+    {%- set ns_f = namespace(found=false) -%}
+    {%- for tc in tcs -%}
+        {%- if id_of(tc) == target -%}
+            {%- set ns_f.found = true -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- if ns_f.found -%}1{%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) -%}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{%- for m in messages -%}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- elif '</think>' in content %}
+    {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
+    {%- set content = content.split('</think>')[-1] %}
+{%- endif %}
+{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
+{{ '<think>' + reasoning_content +  '</think>'}}
+{%- else -%}
+{{ '<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' -}}
+    {%- set block_start = loop.index0 -%}
+    {%- set ns_blk = namespace(end=block_start) -%}
+    {%- for j in range(block_start, messages|length) -%}
+        {%- if messages[j].role == 'tool' -%}
+            {%- set ns_blk.end = j -%}
+        {%- else -%}
+            {%- break -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns_a = namespace(tool_calls=none) -%}
+    {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}
+        {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}
+    {%- endif -%}
+    {%- set ns_chk = namespace(can_sort=true) -%}
+    {%- if not ns_a.tool_calls -%}
+        {%- set ns_chk.can_sort = false -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {%- set m = messages[k] -%}
+            {%- if is_list_of_outputs(m) -%}
+                {%- for entry in m.content -%}
+                    {%- set eid = id_of(entry) -%}
+                    {%- if not eid -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}
+                        {%- set ns_chk.can_sort = false -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {%- set tk_id = id_of(m) -%}
+                {%- if not tk_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- for i in range(ns_a.tool_calls | length) -%}
+            {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}
+            {%- if not tc_id -%}
+                {%- set ns_chk.can_sort = false -%}
+            {%- endif -%}
+            {%- for j in range(i + 1, ns_a.tool_calls | length) -%}
+                {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}
+                    {%- set ns_chk.can_sort = false -%}
+                {%- endif -%}
+            {%- endfor -%}
+    {%- endfor -%}
+    {%- endif -%}
+    {%- if ns_chk.can_sort -%}
+        {%- for tc in ns_a.tool_calls -%}
+            {%- set tc_id = id_of(tc) -%}
+            {%- for k in range(block_start, ns_blk.end + 1) -%}
+                {%- set m = messages[k] -%}
+                {%- if is_list_of_outputs(m) -%}
+                    {%- for entry in m.content -%}
+                        {%- set eid = id_of(entry) -%}
+                        {%- if eid == tc_id -%}
+                            {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%}
+                                {{- tool_references_to_response(entry.output) -}}
+                            {%- else -%}
+                                {{- tool_response(visible_text(entry.output)) -}}
+                            {%- endif -%}
+                        {%- endif -%}
+    {%- endfor -%}
+{%- else -%}
+                    {%- set tk_id = id_of(m) -%}
+                    {%- if tk_id == tc_id -%}
+                        {{- render_tool_response(m) -}}
+                    {%- endif -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endfor -%}
+    {%- else -%}
+        {%- for k in range(block_start, ns_blk.end + 1) -%}
+            {{- render_tool_response(messages[k]) -}}
+        {%- endfor -%}
+    {%- endif -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '<think>' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,1110 @@
+{
+  "architectures": [
+    "Glm5NextForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_end_token_id": 154831,
+  "image_start_token_id": 154830,
+  "image_token_id": 154854,
+  "model_type": "glm5_next",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "nvfp4-pack-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": "local",
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "re:.*mlp\\.experts\\..*(gate|up|down)_proj$"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "nvfp4-pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.mlp.gate_proj",
+      "model.visual.blocks.0.mlp.up_proj",
+      "model.visual.blocks.0.mlp.down_proj",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.mlp.gate_proj",
+      "model.visual.blocks.1.mlp.up_proj",
+      "model.visual.blocks.1.mlp.down_proj",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.mlp.gate_proj",
+      "model.visual.blocks.2.mlp.up_proj",
+      "model.visual.blocks.2.mlp.down_proj",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.mlp.gate_proj",
+      "model.visual.blocks.3.mlp.up_proj",
+      "model.visual.blocks.3.mlp.down_proj",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.mlp.gate_proj",
+      "model.visual.blocks.4.mlp.up_proj",
+      "model.visual.blocks.4.mlp.down_proj",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.mlp.gate_proj",
+      "model.visual.blocks.5.mlp.up_proj",
+      "model.visual.blocks.5.mlp.down_proj",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.mlp.gate_proj",
+      "model.visual.blocks.6.mlp.up_proj",
+      "model.visual.blocks.6.mlp.down_proj",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.mlp.gate_proj",
+      "model.visual.blocks.7.mlp.up_proj",
+      "model.visual.blocks.7.mlp.down_proj",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.mlp.gate_proj",
+      "model.visual.blocks.8.mlp.up_proj",
+      "model.visual.blocks.8.mlp.down_proj",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.mlp.gate_proj",
+      "model.visual.blocks.9.mlp.up_proj",
+      "model.visual.blocks.9.mlp.down_proj",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.mlp.gate_proj",
+      "model.visual.blocks.10.mlp.up_proj",
+      "model.visual.blocks.10.mlp.down_proj",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.mlp.gate_proj",
+      "model.visual.blocks.11.mlp.up_proj",
+      "model.visual.blocks.11.mlp.down_proj",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.mlp.gate_proj",
+      "model.visual.blocks.12.mlp.up_proj",
+      "model.visual.blocks.12.mlp.down_proj",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.mlp.gate_proj",
+      "model.visual.blocks.13.mlp.up_proj",
+      "model.visual.blocks.13.mlp.down_proj",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.mlp.gate_proj",
+      "model.visual.blocks.14.mlp.up_proj",
+      "model.visual.blocks.14.mlp.down_proj",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.mlp.gate_proj",
+      "model.visual.blocks.15.mlp.up_proj",
+      "model.visual.blocks.15.mlp.down_proj",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.mlp.gate_proj",
+      "model.visual.blocks.16.mlp.up_proj",
+      "model.visual.blocks.16.mlp.down_proj",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.mlp.gate_proj",
+      "model.visual.blocks.17.mlp.up_proj",
+      "model.visual.blocks.17.mlp.down_proj",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.mlp.gate_proj",
+      "model.visual.blocks.18.mlp.up_proj",
+      "model.visual.blocks.18.mlp.down_proj",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.mlp.gate_proj",
+      "model.visual.blocks.19.mlp.up_proj",
+      "model.visual.blocks.19.mlp.down_proj",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.mlp.gate_proj",
+      "model.visual.blocks.20.mlp.up_proj",
+      "model.visual.blocks.20.mlp.down_proj",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.mlp.gate_proj",
+      "model.visual.blocks.21.mlp.up_proj",
+      "model.visual.blocks.21.mlp.down_proj",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.mlp.gate_proj",
+      "model.visual.blocks.22.mlp.up_proj",
+      "model.visual.blocks.22.mlp.down_proj",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.mlp.gate_proj",
+      "model.visual.blocks.23.mlp.up_proj",
+      "model.visual.blocks.23.mlp.down_proj",
+      "model.visual.merger.proj",
+      "model.visual.merger.gate_proj",
+      "model.visual.merger.up_proj",
+      "model.visual.merger.down_proj",
+      "model.language_model.layers.0.self_attn.q_proj",
+      "model.language_model.layers.0.self_attn.k_proj",
+      "model.language_model.layers.0.self_attn.v_proj",
+      "model.language_model.layers.0.self_attn.forget_gate",
+      "model.language_model.layers.0.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.0.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.0.self_attn.b_proj",
+      "model.language_model.layers.0.self_attn.g_a_proj",
+      "model.language_model.layers.0.self_attn.g_b_proj",
+      "model.language_model.layers.0.self_attn.o_norm",
+      "model.language_model.layers.0.self_attn.o_proj",
+      "model.language_model.layers.0.mlp.gate_proj",
+      "model.language_model.layers.0.mlp.up_proj",
+      "model.language_model.layers.0.mlp.down_proj",
+      "model.language_model.layers.1.self_attn.q_proj",
+      "model.language_model.layers.1.self_attn.k_proj",
+      "model.language_model.layers.1.self_attn.v_proj",
+      "model.language_model.layers.1.self_attn.forget_gate",
+      "model.language_model.layers.1.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.1.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.1.self_attn.b_proj",
+      "model.language_model.layers.1.self_attn.g_a_proj",
+      "model.language_model.layers.1.self_attn.g_b_proj",
+      "model.language_model.layers.1.self_attn.o_norm",
+      "model.language_model.layers.1.self_attn.o_proj",
+      "model.language_model.layers.1.mlp.gate_proj",
+      "model.language_model.layers.1.mlp.up_proj",
+      "model.language_model.layers.1.mlp.down_proj",
+      "model.language_model.layers.2.self_attn.q_proj",
+      "model.language_model.layers.2.self_attn.k_proj",
+      "model.language_model.layers.2.self_attn.v_proj",
+      "model.language_model.layers.2.self_attn.forget_gate",
+      "model.language_model.layers.2.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.2.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.2.self_attn.b_proj",
+      "model.language_model.layers.2.self_attn.g_a_proj",
+      "model.language_model.layers.2.self_attn.g_b_proj",
+      "model.language_model.layers.2.self_attn.o_norm",
+      "model.language_model.layers.2.self_attn.o_proj",
+      "model.language_model.layers.2.mlp.gate_proj",
+      "model.language_model.layers.2.mlp.up_proj",
+      "model.language_model.layers.2.mlp.down_proj",
+      "model.language_model.layers.3.self_attn.q_a_proj",
+      "model.language_model.layers.3.self_attn.q_b_proj",
+      "model.language_model.layers.3.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.3.self_attn.kv_b_proj",
+      "model.language_model.layers.3.self_attn.o_proj",
+      "model.language_model.layers.3.self_attn.indexer.wq_b",
+      "model.language_model.layers.3.self_attn.indexer.wk",
+      "model.language_model.layers.3.self_attn.indexer.weights_proj",
+      "model.language_model.layers.3.mlp.gate",
+      "model.language_model.layers.3.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.3.mlp.shared_experts.up_proj",
+      "model.language_model.layers.3.mlp.shared_experts.down_proj",
+      "model.language_model.layers.4.self_attn.q_proj",
+      "model.language_model.layers.4.self_attn.k_proj",
+      "model.language_model.layers.4.self_attn.v_proj",
+      "model.language_model.layers.4.self_attn.forget_gate",
+      "model.language_model.layers.4.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.4.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.4.self_attn.b_proj",
+      "model.language_model.layers.4.self_attn.g_a_proj",
+      "model.language_model.layers.4.self_attn.g_b_proj",
+      "model.language_model.layers.4.self_attn.o_norm",
+      "model.language_model.layers.4.self_attn.o_proj",
+      "model.language_model.layers.4.mlp.gate",
+      "model.language_model.layers.4.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.4.mlp.shared_experts.up_proj",
+      "model.language_model.layers.4.mlp.shared_experts.down_proj",
+      "model.language_model.layers.5.self_attn.q_proj",
+      "model.language_model.layers.5.self_attn.k_proj",
+      "model.language_model.layers.5.self_attn.v_proj",
+      "model.language_model.layers.5.self_attn.forget_gate",
+      "model.language_model.layers.5.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.5.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.5.self_attn.b_proj",
+      "model.language_model.layers.5.self_attn.g_a_proj",
+      "model.language_model.layers.5.self_attn.g_b_proj",
+      "model.language_model.layers.5.self_attn.o_norm",
+      "model.language_model.layers.5.self_attn.o_proj",
+      "model.language_model.layers.5.mlp.gate",
+      "model.language_model.layers.5.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.5.mlp.shared_experts.up_proj",
+      "model.language_model.layers.5.mlp.shared_experts.down_proj",
+      "model.language_model.layers.6.self_attn.q_proj",
+      "model.language_model.layers.6.self_attn.k_proj",
+      "model.language_model.layers.6.self_attn.v_proj",
+      "model.language_model.layers.6.self_attn.forget_gate",
+      "model.language_model.layers.6.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.6.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.6.self_attn.b_proj",
+      "model.language_model.layers.6.self_attn.g_a_proj",
+      "model.language_model.layers.6.self_attn.g_b_proj",
+      "model.language_model.layers.6.self_attn.o_norm",
+      "model.language_model.layers.6.self_attn.o_proj",
+      "model.language_model.layers.6.mlp.gate",
+      "model.language_model.layers.6.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.6.mlp.shared_experts.up_proj",
+      "model.language_model.layers.6.mlp.shared_experts.down_proj",
+      "model.language_model.layers.7.self_attn.q_a_proj",
+      "model.language_model.layers.7.self_attn.q_b_proj",
+      "model.language_model.layers.7.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.7.self_attn.kv_b_proj",
+      "model.language_model.layers.7.self_attn.o_proj",
+      "model.language_model.layers.7.self_attn.indexer.wq_b",
+      "model.language_model.layers.7.self_attn.indexer.wk",
+      "model.language_model.layers.7.self_attn.indexer.weights_proj",
+      "model.language_model.layers.7.mlp.gate",
+      "model.language_model.layers.7.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.7.mlp.shared_experts.up_proj",
+      "model.language_model.layers.7.mlp.shared_experts.down_proj",
+      "model.language_model.layers.8.self_attn.q_proj",
+      "model.language_model.layers.8.self_attn.k_proj",
+      "model.language_model.layers.8.self_attn.v_proj",
+      "model.language_model.layers.8.self_attn.forget_gate",
+      "model.language_model.layers.8.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.8.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.8.self_attn.b_proj",
+      "model.language_model.layers.8.self_attn.g_a_proj",
+      "model.language_model.layers.8.self_attn.g_b_proj",
+      "model.language_model.layers.8.self_attn.o_norm",
+      "model.language_model.layers.8.self_attn.o_proj",
+      "model.language_model.layers.8.mlp.gate",
+      "model.language_model.layers.8.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.8.mlp.shared_experts.up_proj",
+      "model.language_model.layers.8.mlp.shared_experts.down_proj",
+      "model.language_model.layers.9.self_attn.q_proj",
+      "model.language_model.layers.9.self_attn.k_proj",
+      "model.language_model.layers.9.self_attn.v_proj",
+      "model.language_model.layers.9.self_attn.forget_gate",
+      "model.language_model.layers.9.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.9.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.9.self_attn.b_proj",
+      "model.language_model.layers.9.self_attn.g_a_proj",
+      "model.language_model.layers.9.self_attn.g_b_proj",
+      "model.language_model.layers.9.self_attn.o_norm",
+      "model.language_model.layers.9.self_attn.o_proj",
+      "model.language_model.layers.9.mlp.gate",
+      "model.language_model.layers.9.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.9.mlp.shared_experts.up_proj",
+      "model.language_model.layers.9.mlp.shared_experts.down_proj",
+      "model.language_model.layers.10.self_attn.q_proj",
+      "model.language_model.layers.10.self_attn.k_proj",
+      "model.language_model.layers.10.self_attn.v_proj",
+      "model.language_model.layers.10.self_attn.forget_gate",
+      "model.language_model.layers.10.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.10.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.10.self_attn.b_proj",
+      "model.language_model.layers.10.self_attn.g_a_proj",
+      "model.language_model.layers.10.self_attn.g_b_proj",
+      "model.language_model.layers.10.self_attn.o_norm",
+      "model.language_model.layers.10.self_attn.o_proj",
+      "model.language_model.layers.10.mlp.gate",
+      "model.language_model.layers.10.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.10.mlp.shared_experts.up_proj",
+      "model.language_model.layers.10.mlp.shared_experts.down_proj",
+      "model.language_model.layers.11.self_attn.q_a_proj",
+      "model.language_model.layers.11.self_attn.q_b_proj",
+      "model.language_model.layers.11.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.11.self_attn.kv_b_proj",
+      "model.language_model.layers.11.self_attn.o_proj",
+      "model.language_model.layers.11.self_attn.indexer.wq_b",
+      "model.language_model.layers.11.self_attn.indexer.wk",
+      "model.language_model.layers.11.self_attn.indexer.weights_proj",
+      "model.language_model.layers.11.mlp.gate",
+      "model.language_model.layers.11.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.11.mlp.shared_experts.up_proj",
+      "model.language_model.layers.11.mlp.shared_experts.down_proj",
+      "model.language_model.layers.12.self_attn.q_proj",
+      "model.language_model.layers.12.self_attn.k_proj",
+      "model.language_model.layers.12.self_attn.v_proj",
+      "model.language_model.layers.12.self_attn.forget_gate",
+      "model.language_model.layers.12.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.12.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.12.self_attn.b_proj",
+      "model.language_model.layers.12.self_attn.g_a_proj",
+      "model.language_model.layers.12.self_attn.g_b_proj",
+      "model.language_model.layers.12.self_attn.o_norm",
+      "model.language_model.layers.12.self_attn.o_proj",
+      "model.language_model.layers.12.mlp.gate",
+      "model.language_model.layers.12.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.12.mlp.shared_experts.up_proj",
+      "model.language_model.layers.12.mlp.shared_experts.down_proj",
+      "model.language_model.layers.13.self_attn.q_proj",
+      "model.language_model.layers.13.self_attn.k_proj",
+      "model.language_model.layers.13.self_attn.v_proj",
+      "model.language_model.layers.13.self_attn.forget_gate",
+      "model.language_model.layers.13.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.13.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.13.self_attn.b_proj",
+      "model.language_model.layers.13.self_attn.g_a_proj",
+      "model.language_model.layers.13.self_attn.g_b_proj",
+      "model.language_model.layers.13.self_attn.o_norm",
+      "model.language_model.layers.13.self_attn.o_proj",
+      "model.language_model.layers.13.mlp.gate",
+      "model.language_model.layers.13.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.13.mlp.shared_experts.up_proj",
+      "model.language_model.layers.13.mlp.shared_experts.down_proj",
+      "model.language_model.layers.14.self_attn.q_proj",
+      "model.language_model.layers.14.self_attn.k_proj",
+      "model.language_model.layers.14.self_attn.v_proj",
+      "model.language_model.layers.14.self_attn.forget_gate",
+      "model.language_model.layers.14.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.14.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.14.self_attn.b_proj",
+      "model.language_model.layers.14.self_attn.g_a_proj",
+      "model.language_model.layers.14.self_attn.g_b_proj",
+      "model.language_model.layers.14.self_attn.o_norm",
+      "model.language_model.layers.14.self_attn.o_proj",
+      "model.language_model.layers.14.mlp.gate",
+      "model.language_model.layers.14.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.14.mlp.shared_experts.up_proj",
+      "model.language_model.layers.14.mlp.shared_experts.down_proj",
+      "model.language_model.layers.15.self_attn.q_a_proj",
+      "model.language_model.layers.15.self_attn.q_b_proj",
+      "model.language_model.layers.15.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.15.self_attn.kv_b_proj",
+      "model.language_model.layers.15.self_attn.o_proj",
+      "model.language_model.layers.15.self_attn.indexer.wq_b",
+      "model.language_model.layers.15.self_attn.indexer.wk",
+      "model.language_model.layers.15.self_attn.indexer.weights_proj",
+      "model.language_model.layers.15.mlp.gate",
+      "model.language_model.layers.15.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.15.mlp.shared_experts.up_proj",
+      "model.language_model.layers.15.mlp.shared_experts.down_proj",
+      "model.language_model.layers.16.self_attn.q_proj",
+      "model.language_model.layers.16.self_attn.k_proj",
+      "model.language_model.layers.16.self_attn.v_proj",
+      "model.language_model.layers.16.self_attn.forget_gate",
+      "model.language_model.layers.16.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.16.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.16.self_attn.b_proj",
+      "model.language_model.layers.16.self_attn.g_a_proj",
+      "model.language_model.layers.16.self_attn.g_b_proj",
+      "model.language_model.layers.16.self_attn.o_norm",
+      "model.language_model.layers.16.self_attn.o_proj",
+      "model.language_model.layers.16.mlp.gate",
+      "model.language_model.layers.16.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.16.mlp.shared_experts.up_proj",
+      "model.language_model.layers.16.mlp.shared_experts.down_proj",
+      "model.language_model.layers.17.self_attn.q_proj",
+      "model.language_model.layers.17.self_attn.k_proj",
+      "model.language_model.layers.17.self_attn.v_proj",
+      "model.language_model.layers.17.self_attn.forget_gate",
+      "model.language_model.layers.17.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.17.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.17.self_attn.b_proj",
+      "model.language_model.layers.17.self_attn.g_a_proj",
+      "model.language_model.layers.17.self_attn.g_b_proj",
+      "model.language_model.layers.17.self_attn.o_norm",
+      "model.language_model.layers.17.self_attn.o_proj",
+      "model.language_model.layers.17.mlp.gate",
+      "model.language_model.layers.17.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.17.mlp.shared_experts.up_proj",
+      "model.language_model.layers.17.mlp.shared_experts.down_proj",
+      "model.language_model.layers.18.self_attn.q_proj",
+      "model.language_model.layers.18.self_attn.k_proj",
+      "model.language_model.layers.18.self_attn.v_proj",
+      "model.language_model.layers.18.self_attn.forget_gate",
+      "model.language_model.layers.18.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.18.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.18.self_attn.b_proj",
+      "model.language_model.layers.18.self_attn.g_a_proj",
+      "model.language_model.layers.18.self_attn.g_b_proj",
+      "model.language_model.layers.18.self_attn.o_norm",
+      "model.language_model.layers.18.self_attn.o_proj",
+      "model.language_model.layers.18.mlp.gate",
+      "model.language_model.layers.18.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.18.mlp.shared_experts.up_proj",
+      "model.language_model.layers.18.mlp.shared_experts.down_proj",
+      "model.language_model.layers.19.self_attn.q_a_proj",
+      "model.language_model.layers.19.self_attn.q_b_proj",
+      "model.language_model.layers.19.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.19.self_attn.kv_b_proj",
+      "model.language_model.layers.19.self_attn.o_proj",
+      "model.language_model.layers.19.self_attn.indexer.wq_b",
+      "model.language_model.layers.19.self_attn.indexer.wk",
+      "model.language_model.layers.19.self_attn.indexer.weights_proj",
+      "model.language_model.layers.19.mlp.gate",
+      "model.language_model.layers.19.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.19.mlp.shared_experts.up_proj",
+      "model.language_model.layers.19.mlp.shared_experts.down_proj",
+      "model.language_model.layers.20.self_attn.q_proj",
+      "model.language_model.layers.20.self_attn.k_proj",
+      "model.language_model.layers.20.self_attn.v_proj",
+      "model.language_model.layers.20.self_attn.forget_gate",
+      "model.language_model.layers.20.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.20.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.20.self_attn.b_proj",
+      "model.language_model.layers.20.self_attn.g_a_proj",
+      "model.language_model.layers.20.self_attn.g_b_proj",
+      "model.language_model.layers.20.self_attn.o_norm",
+      "model.language_model.layers.20.self_attn.o_proj",
+      "model.language_model.layers.20.mlp.gate",
+      "model.language_model.layers.20.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.20.mlp.shared_experts.up_proj",
+      "model.language_model.layers.20.mlp.shared_experts.down_proj",
+      "model.language_model.layers.21.self_attn.q_proj",
+      "model.language_model.layers.21.self_attn.k_proj",
+      "model.language_model.layers.21.self_attn.v_proj",
+      "model.language_model.layers.21.self_attn.forget_gate",
+      "model.language_model.layers.21.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.21.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.21.self_attn.b_proj",
+      "model.language_model.layers.21.self_attn.g_a_proj",
+      "model.language_model.layers.21.self_attn.g_b_proj",
+      "model.language_model.layers.21.self_attn.o_norm",
+      "model.language_model.layers.21.self_attn.o_proj",
+      "model.language_model.layers.21.mlp.gate",
+      "model.language_model.layers.21.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.21.mlp.shared_experts.up_proj",
+      "model.language_model.layers.21.mlp.shared_experts.down_proj",
+      "model.language_model.layers.22.self_attn.q_proj",
+      "model.language_model.layers.22.self_attn.k_proj",
+      "model.language_model.layers.22.self_attn.v_proj",
+      "model.language_model.layers.22.self_attn.forget_gate",
+      "model.language_model.layers.22.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.22.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.22.self_attn.b_proj",
+      "model.language_model.layers.22.self_attn.g_a_proj",
+      "model.language_model.layers.22.self_attn.g_b_proj",
+      "model.language_model.layers.22.self_attn.o_norm",
+      "model.language_model.layers.22.self_attn.o_proj",
+      "model.language_model.layers.22.mlp.gate",
+      "model.language_model.layers.22.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.22.mlp.shared_experts.up_proj",
+      "model.language_model.layers.22.mlp.shared_experts.down_proj",
+      "model.language_model.layers.23.self_attn.q_a_proj",
+      "model.language_model.layers.23.self_attn.q_b_proj",
+      "model.language_model.layers.23.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.23.self_attn.kv_b_proj",
+      "model.language_model.layers.23.self_attn.o_proj",
+      "model.language_model.layers.23.self_attn.indexer.wq_b",
+      "model.language_model.layers.23.self_attn.indexer.wk",
+      "model.language_model.layers.23.self_attn.indexer.weights_proj",
+      "model.language_model.layers.23.mlp.gate",
+      "model.language_model.layers.23.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.23.mlp.shared_experts.up_proj",
+      "model.language_model.layers.23.mlp.shared_experts.down_proj",
+      "model.language_model.layers.24.self_attn.q_proj",
+      "model.language_model.layers.24.self_attn.k_proj",
+      "model.language_model.layers.24.self_attn.v_proj",
+      "model.language_model.layers.24.self_attn.forget_gate",
+      "model.language_model.layers.24.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.24.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.24.self_attn.b_proj",
+      "model.language_model.layers.24.self_attn.g_a_proj",
+      "model.language_model.layers.24.self_attn.g_b_proj",
+      "model.language_model.layers.24.self_attn.o_norm",
+      "model.language_model.layers.24.self_attn.o_proj",
+      "model.language_model.layers.24.mlp.gate",
+      "model.language_model.layers.24.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.24.mlp.shared_experts.up_proj",
+      "model.language_model.layers.24.mlp.shared_experts.down_proj",
+      "model.language_model.layers.25.self_attn.q_proj",
+      "model.language_model.layers.25.self_attn.k_proj",
+      "model.language_model.layers.25.self_attn.v_proj",
+      "model.language_model.layers.25.self_attn.forget_gate",
+      "model.language_model.layers.25.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.25.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.25.self_attn.b_proj",
+      "model.language_model.layers.25.self_attn.g_a_proj",
+      "model.language_model.layers.25.self_attn.g_b_proj",
+      "model.language_model.layers.25.self_attn.o_norm",
+      "model.language_model.layers.25.self_attn.o_proj",
+      "model.language_model.layers.25.mlp.gate",
+      "model.language_model.layers.25.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.25.mlp.shared_experts.up_proj",
+      "model.language_model.layers.25.mlp.shared_experts.down_proj",
+      "model.language_model.layers.26.self_attn.q_proj",
+      "model.language_model.layers.26.self_attn.k_proj",
+      "model.language_model.layers.26.self_attn.v_proj",
+      "model.language_model.layers.26.self_attn.forget_gate",
+      "model.language_model.layers.26.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.26.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.26.self_attn.b_proj",
+      "model.language_model.layers.26.self_attn.g_a_proj",
+      "model.language_model.layers.26.self_attn.g_b_proj",
+      "model.language_model.layers.26.self_attn.o_norm",
+      "model.language_model.layers.26.self_attn.o_proj",
+      "model.language_model.layers.26.mlp.gate",
+      "model.language_model.layers.26.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.26.mlp.shared_experts.up_proj",
+      "model.language_model.layers.26.mlp.shared_experts.down_proj",
+      "model.language_model.layers.27.self_attn.q_a_proj",
+      "model.language_model.layers.27.self_attn.q_b_proj",
+      "model.language_model.layers.27.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.27.self_attn.kv_b_proj",
+      "model.language_model.layers.27.self_attn.o_proj",
+      "model.language_model.layers.27.self_attn.indexer.wq_b",
+      "model.language_model.layers.27.self_attn.indexer.wk",
+      "model.language_model.layers.27.self_attn.indexer.weights_proj",
+      "model.language_model.layers.27.mlp.gate",
+      "model.language_model.layers.27.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.27.mlp.shared_experts.up_proj",
+      "model.language_model.layers.27.mlp.shared_experts.down_proj",
+      "model.language_model.layers.28.self_attn.q_proj",
+      "model.language_model.layers.28.self_attn.k_proj",
+      "model.language_model.layers.28.self_attn.v_proj",
+      "model.language_model.layers.28.self_attn.forget_gate",
+      "model.language_model.layers.28.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.28.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.28.self_attn.b_proj",
+      "model.language_model.layers.28.self_attn.g_a_proj",
+      "model.language_model.layers.28.self_attn.g_b_proj",
+      "model.language_model.layers.28.self_attn.o_norm",
+      "model.language_model.layers.28.self_attn.o_proj",
+      "model.language_model.layers.28.mlp.gate",
+      "model.language_model.layers.28.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.28.mlp.shared_experts.up_proj",
+      "model.language_model.layers.28.mlp.shared_experts.down_proj",
+      "model.language_model.layers.29.self_attn.q_proj",
+      "model.language_model.layers.29.self_attn.k_proj",
+      "model.language_model.layers.29.self_attn.v_proj",
+      "model.language_model.layers.29.self_attn.forget_gate",
+      "model.language_model.layers.29.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.29.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.29.self_attn.b_proj",
+      "model.language_model.layers.29.self_attn.g_a_proj",
+      "model.language_model.layers.29.self_attn.g_b_proj",
+      "model.language_model.layers.29.self_attn.o_norm",
+      "model.language_model.layers.29.self_attn.o_proj",
+      "model.language_model.layers.29.mlp.gate",
+      "model.language_model.layers.29.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.29.mlp.shared_experts.up_proj",
+      "model.language_model.layers.29.mlp.shared_experts.down_proj",
+      "model.language_model.layers.30.self_attn.q_proj",
+      "model.language_model.layers.30.self_attn.k_proj",
+      "model.language_model.layers.30.self_attn.v_proj",
+      "model.language_model.layers.30.self_attn.forget_gate",
+      "model.language_model.layers.30.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.30.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.30.self_attn.b_proj",
+      "model.language_model.layers.30.self_attn.g_a_proj",
+      "model.language_model.layers.30.self_attn.g_b_proj",
+      "model.language_model.layers.30.self_attn.o_norm",
+      "model.language_model.layers.30.self_attn.o_proj",
+      "model.language_model.layers.30.mlp.gate",
+      "model.language_model.layers.30.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.30.mlp.shared_experts.up_proj",
+      "model.language_model.layers.30.mlp.shared_experts.down_proj",
+      "model.language_model.layers.31.self_attn.q_a_proj",
+      "model.language_model.layers.31.self_attn.q_b_proj",
+      "model.language_model.layers.31.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.31.self_attn.kv_b_proj",
+      "model.language_model.layers.31.self_attn.o_proj",
+      "model.language_model.layers.31.self_attn.indexer.wq_b",
+      "model.language_model.layers.31.self_attn.indexer.wk",
+      "model.language_model.layers.31.self_attn.indexer.weights_proj",
+      "model.language_model.layers.31.mlp.gate",
+      "model.language_model.layers.31.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.31.mlp.shared_experts.up_proj",
+      "model.language_model.layers.31.mlp.shared_experts.down_proj",
+      "model.language_model.layers.32.self_attn.q_proj",
+      "model.language_model.layers.32.self_attn.k_proj",
+      "model.language_model.layers.32.self_attn.v_proj",
+      "model.language_model.layers.32.self_attn.forget_gate",
+      "model.language_model.layers.32.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.32.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.32.self_attn.b_proj",
+      "model.language_model.layers.32.self_attn.g_a_proj",
+      "model.language_model.layers.32.self_attn.g_b_proj",
+      "model.language_model.layers.32.self_attn.o_norm",
+      "model.language_model.layers.32.self_attn.o_proj",
+      "model.language_model.layers.32.mlp.gate",
+      "model.language_model.layers.32.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.32.mlp.shared_experts.up_proj",
+      "model.language_model.layers.32.mlp.shared_experts.down_proj",
+      "model.language_model.layers.33.self_attn.q_proj",
+      "model.language_model.layers.33.self_attn.k_proj",
+      "model.language_model.layers.33.self_attn.v_proj",
+      "model.language_model.layers.33.self_attn.forget_gate",
+      "model.language_model.layers.33.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.33.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.33.self_attn.b_proj",
+      "model.language_model.layers.33.self_attn.g_a_proj",
+      "model.language_model.layers.33.self_attn.g_b_proj",
+      "model.language_model.layers.33.self_attn.o_norm",
+      "model.language_model.layers.33.self_attn.o_proj",
+      "model.language_model.layers.33.mlp.gate",
+      "model.language_model.layers.33.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.33.mlp.shared_experts.up_proj",
+      "model.language_model.layers.33.mlp.shared_experts.down_proj",
+      "model.language_model.layers.34.self_attn.q_proj",
+      "model.language_model.layers.34.self_attn.k_proj",
+      "model.language_model.layers.34.self_attn.v_proj",
+      "model.language_model.layers.34.self_attn.forget_gate",
+      "model.language_model.layers.34.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.34.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.34.self_attn.b_proj",
+      "model.language_model.layers.34.self_attn.g_a_proj",
+      "model.language_model.layers.34.self_attn.g_b_proj",
+      "model.language_model.layers.34.self_attn.o_norm",
+      "model.language_model.layers.34.self_attn.o_proj",
+      "model.language_model.layers.34.mlp.gate",
+      "model.language_model.layers.34.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.34.mlp.shared_experts.up_proj",
+      "model.language_model.layers.34.mlp.shared_experts.down_proj",
+      "model.language_model.layers.35.self_attn.q_a_proj",
+      "model.language_model.layers.35.self_attn.q_b_proj",
+      "model.language_model.layers.35.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.35.self_attn.kv_b_proj",
+      "model.language_model.layers.35.self_attn.o_proj",
+      "model.language_model.layers.35.self_attn.indexer.wq_b",
+      "model.language_model.layers.35.self_attn.indexer.wk",
+      "model.language_model.layers.35.self_attn.indexer.weights_proj",
+      "model.language_model.layers.35.mlp.gate",
+      "model.language_model.layers.35.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.35.mlp.shared_experts.up_proj",
+      "model.language_model.layers.35.mlp.shared_experts.down_proj",
+      "model.language_model.layers.36.self_attn.q_proj",
+      "model.language_model.layers.36.self_attn.k_proj",
+      "model.language_model.layers.36.self_attn.v_proj",
+      "model.language_model.layers.36.self_attn.forget_gate",
+      "model.language_model.layers.36.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.36.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.36.self_attn.b_proj",
+      "model.language_model.layers.36.self_attn.g_a_proj",
+      "model.language_model.layers.36.self_attn.g_b_proj",
+      "model.language_model.layers.36.self_attn.o_norm",
+      "model.language_model.layers.36.self_attn.o_proj",
+      "model.language_model.layers.36.mlp.gate",
+      "model.language_model.layers.36.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.36.mlp.shared_experts.up_proj",
+      "model.language_model.layers.36.mlp.shared_experts.down_proj",
+      "model.language_model.layers.37.self_attn.q_proj",
+      "model.language_model.layers.37.self_attn.k_proj",
+      "model.language_model.layers.37.self_attn.v_proj",
+      "model.language_model.layers.37.self_attn.forget_gate",
+      "model.language_model.layers.37.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.37.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.37.self_attn.b_proj",
+      "model.language_model.layers.37.self_attn.g_a_proj",
+      "model.language_model.layers.37.self_attn.g_b_proj",
+      "model.language_model.layers.37.self_attn.o_norm",
+      "model.language_model.layers.37.self_attn.o_proj",
+      "model.language_model.layers.37.mlp.gate",
+      "model.language_model.layers.37.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.37.mlp.shared_experts.up_proj",
+      "model.language_model.layers.37.mlp.shared_experts.down_proj",
+      "model.language_model.layers.38.self_attn.q_proj",
+      "model.language_model.layers.38.self_attn.k_proj",
+      "model.language_model.layers.38.self_attn.v_proj",
+      "model.language_model.layers.38.self_attn.forget_gate",
+      "model.language_model.layers.38.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.38.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.38.self_attn.b_proj",
+      "model.language_model.layers.38.self_attn.g_a_proj",
+      "model.language_model.layers.38.self_attn.g_b_proj",
+      "model.language_model.layers.38.self_attn.o_norm",
+      "model.language_model.layers.38.self_attn.o_proj",
+      "model.language_model.layers.38.mlp.gate",
+      "model.language_model.layers.38.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.38.mlp.shared_experts.up_proj",
+      "model.language_model.layers.38.mlp.shared_experts.down_proj",
+      "model.language_model.layers.39.self_attn.q_a_proj",
+      "model.language_model.layers.39.self_attn.q_b_proj",
+      "model.language_model.layers.39.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.39.self_attn.kv_b_proj",
+      "model.language_model.layers.39.self_attn.o_proj",
+      "model.language_model.layers.39.self_attn.indexer.wq_b",
+      "model.language_model.layers.39.self_attn.indexer.wk",
+      "model.language_model.layers.39.self_attn.indexer.weights_proj",
+      "model.language_model.layers.39.mlp.gate",
+      "model.language_model.layers.39.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.39.mlp.shared_experts.up_proj",
+      "model.language_model.layers.39.mlp.shared_experts.down_proj",
+      "model.language_model.layers.40.self_attn.q_proj",
+      "model.language_model.layers.40.self_attn.k_proj",
+      "model.language_model.layers.40.self_attn.v_proj",
+      "model.language_model.layers.40.self_attn.forget_gate",
+      "model.language_model.layers.40.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.40.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.40.self_attn.b_proj",
+      "model.language_model.layers.40.self_attn.g_a_proj",
+      "model.language_model.layers.40.self_attn.g_b_proj",
+      "model.language_model.layers.40.self_attn.o_norm",
+      "model.language_model.layers.40.self_attn.o_proj",
+      "model.language_model.layers.40.mlp.gate",
+      "model.language_model.layers.40.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.40.mlp.shared_experts.up_proj",
+      "model.language_model.layers.40.mlp.shared_experts.down_proj",
+      "model.language_model.layers.41.self_attn.q_proj",
+      "model.language_model.layers.41.self_attn.k_proj",
+      "model.language_model.layers.41.self_attn.v_proj",
+      "model.language_model.layers.41.self_attn.forget_gate",
+      "model.language_model.layers.41.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.41.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.41.self_attn.b_proj",
+      "model.language_model.layers.41.self_attn.g_a_proj",
+      "model.language_model.layers.41.self_attn.g_b_proj",
+      "model.language_model.layers.41.self_attn.o_norm",
+      "model.language_model.layers.41.self_attn.o_proj",
+      "model.language_model.layers.41.mlp.gate",
+      "model.language_model.layers.41.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.41.mlp.shared_experts.up_proj",
+      "model.language_model.layers.41.mlp.shared_experts.down_proj",
+      "model.language_model.layers.42.self_attn.q_proj",
+      "model.language_model.layers.42.self_attn.k_proj",
+      "model.language_model.layers.42.self_attn.v_proj",
+      "model.language_model.layers.42.self_attn.forget_gate",
+      "model.language_model.layers.42.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.42.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.42.self_attn.b_proj",
+      "model.language_model.layers.42.self_attn.g_a_proj",
+      "model.language_model.layers.42.self_attn.g_b_proj",
+      "model.language_model.layers.42.self_attn.o_norm",
+      "model.language_model.layers.42.self_attn.o_proj",
+      "model.language_model.layers.42.mlp.gate",
+      "model.language_model.layers.42.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.42.mlp.shared_experts.up_proj",
+      "model.language_model.layers.42.mlp.shared_experts.down_proj",
+      "model.language_model.layers.43.self_attn.q_a_proj",
+      "model.language_model.layers.43.self_attn.q_b_proj",
+      "model.language_model.layers.43.self_attn.kv_a_proj_with_mqa",
+      "model.language_model.layers.43.self_attn.kv_b_proj",
+      "model.language_model.layers.43.self_attn.o_proj",
+      "model.language_model.layers.43.self_attn.indexer.wq_b",
+      "model.language_model.layers.43.self_attn.indexer.wk",
+      "model.language_model.layers.43.self_attn.indexer.weights_proj",
+      "model.language_model.layers.43.mlp.gate",
+      "model.language_model.layers.43.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.43.mlp.shared_experts.up_proj",
+      "model.language_model.layers.43.mlp.shared_experts.down_proj",
+      "model.language_model.layers.44.self_attn.q_proj",
+      "model.language_model.layers.44.self_attn.k_proj",
+      "model.language_model.layers.44.self_attn.v_proj",
+      "model.language_model.layers.44.self_attn.forget_gate",
+      "model.language_model.layers.44.self_attn.forget_gate.f_a_proj",
+      "model.language_model.layers.44.self_attn.forget_gate.f_b_proj",
+      "model.language_model.layers.44.self_attn.b_proj",
+      "model.language_model.layers.44.self_attn.g_a_proj",
+      "model.language_model.layers.44.self_attn.g_b_proj",
+      "model.language_model.layers.44.self_attn.o_norm",
+      "model.language_model.layers.44.self_attn.o_proj",
+      "model.language_model.layers.44.mlp.gate",
+      "model.language_model.layers.44.mlp.shared_experts.gate_proj",
+      "model.language_model.layers.44.mlp.shared_experts.up_proj",
+      "model.language_model.layers.44.mlp.shared_experts.down_proj",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.17.2.dev32+g46196ce"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+      154820,
+      154827,
+      154829
+    ],
+    "first_k_dense_replace": 3,
+    "hc_eps": 1e-06,
+    "hc_mult": 4,
+    "hc_sinkhorn_iters": 20,
+    "head_dim": 0,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "index_head_dim": 128,
+    "index_kpool": 4,
+    "index_kpool_always_select_tail": true,
+    "index_kpool_compress": true,
+    "index_n_heads": 32,
+    "index_share_for_mtp_iteration": true,
+    "index_topk": 2048,
+    "indexer_rope_interleave": true,
+    "indexer_types": [
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full",
+      "full"
+    ],
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "kv_lora_rank": 512,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "deepseek_sparse_attention",
+      "linear_attention"
+    ],
+    "linear_attn_config": {
+      "full_attn_layers": [
+        3,
+        7,
+        11,
+        15,
+        19,
+        23,
+        27,
+        31,
+        35,
+        39,
+        43
+      ],
+      "gate_lower_bound": -5.0,
+      "head_dim": 128,
+      "kda_layers": [
+        0,
+        1,
+        2,
+        4,
+        5,
+        6,
+        8,
+        9,
+        10,
+        12,
+        13,
+        14,
+        16,
+        17,
+        18,
+        20,
+        21,
+        22,
+        24,
+        25,
+        26,
+        28,
+        29,
+        30,
+        32,
+        33,
+        34,
+        36,
+        37,
+        38,
+        40,
+        41,
+        42,
+        44
+      ],
+      "num_heads": 64,
+      "short_conv_kernel_size": 4
+    },
+    "linear_conv_kernel_dim": 4,
+    "linear_head_dim": 128,
+    "linear_lower_bound": -5.0,
+    "linear_num_heads": 64,
+    "max_position_embeddings": 1048576,
+    "mhc": true,
+    "mla_use_nope": true,
+    "mlp_layer_types": [
+      "dense",
+      "dense",
+      "dense",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse",
+      "sparse"
+    ],
+    "model_type": "glm5_next_text",
+    "moe_intermediate_size": 2048,
+    "moe_router_dtype": "float32",
+    "n_group": 1,
+    "n_routed_experts": 288,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 45,
+    "num_key_value_heads": 64,
+    "num_nextn_predict_layers": 1,
+    "output_router_logits": false,
+    "pad_token_id": 154820,
+    "q_lora_rank": 1536,
+    "qk_head_dim": 256,
+    "qk_nope_head_dim": 256,
+    "qk_rope_head_dim": 0,
+    "rms_norm_eps": 1e-05,
+    "routed_scaling_factor": 2.5,
+    "router_aux_loss_coef": 0.001,
+    "scoring_func": "sigmoid",
+    "swiglu_limit": 10.0,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "use_cache": true,
+    "v_head_dim": 256,
+    "vocab_size": 154880
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.1",
+  "video_end_token_id": 154833,
+  "video_start_token_id": 154832,
+  "video_token_id": 154855,
+  "vision_config": {
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 448,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "glm5_next_vision",
+    "num_heads": 16,
+    "out_hidden_size": 4096,
+    "patch_size": 14,
+    "projection_intermediate_size": 10240,
+    "rms_norm_eps": 1e-05,
+    "spatial_merge_size": 2,
+    "swiglu_limit": 10.0,
+    "temporal_patch_size": 2
+  }
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "transformers_version": "5.16.1"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6846fb90f68505d54dc143c517cfb6dc5e6e0e83d1335942027a8c54369abb
+size 20002894272

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8316bca081630a5a6b2c8cf6a2a760e9f409649d7759d3dbc9777d9d91bcca2
+size 20002803476

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b085e5e14cdfaff92c6efba2eede93ea5d370deffb36ec20ba31b4bb8883c6
+size 20000726256

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97dca208b01884ffe6ae377553a773ba210094423e1b04580ebdebce55c21226
+size 20000334356

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1de5e06341aa90245bb40809847fee322c6548ec323f1889ead226f74c5c34
+size 20000724512

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6d80bdafe7a29ca9218086b9e02b6731f2358d80c18f78f8d86a1ad271b2cf
+size 20000331556

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77c2e31860a92dea8be84fadb8b13a3932205bf0241a3944d4f055752b7bb4d
+size 20000725168

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0dc21ce2b1da1739e974cd2736a6fbdc58ddc0551dc5569f679ee5e7f63da93
+size 20000332348

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11d8fdd3694491fa2c5a6fb47a28197f020a861ff194153d47a6bb8eeb7609a
+size 20000722232

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2519e9daf2c153555e2ecd5d408edb0175c507d094729b55d9092d1385b382b6
+size 10215657876

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42e3ccb127abb24a914eeed0fcd51ccb80eecaabb7d3e5550bfb1f3cdfd2027
+size 16884180

recipe.yaml

@@ -0,0 +1,38 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      config_groups:
+        experts:
+          targets: ['re:.*mlp\.experts\..*(gate|up|down)_proj$']
+          weights:
+            num_bits: 4
+            type: float
+            symmetric: true
+            group_size: 16
+            strategy: tensor_group
+            block_structure: null
+            dynamic: false
+            actorder: null
+            scale_dtype: torch.float8_e4m3fn
+            zp_dtype: null
+            observer: memoryless_minmax
+            observer_kwargs: {}
+          input_activations:
+            num_bits: 4
+            type: float
+            symmetric: true
+            group_size: 16
+            strategy: tensor_group
+            block_structure: null
+            dynamic: local
+            actorder: null
+            scale_dtype: torch.float8_e4m3fn
+            zp_dtype: null
+            observer: static_minmax
+            observer_kwargs: {}
+          output_activations: null
+          format: null
+      targets: [Linear]
+      ignore: ['re:.*visual.*', lm_head, 're:.*mlp\.gate$', 're:.*self_attn\.indexer\..*']
+      bypass_divisibility_checks: false
+      requires_calibration_data: true

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfe2c099a7702a0921abc315ee039deb51e4a34b4818fc509bd27fa3dc4acc1
+size 20217541

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1048576,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}