Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,6 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+quantization_config.json filter=lfs diff=lfs merge=lfs -text

CRACK_SURGERY.json

@@ -0,0 +1,298 @@
+{
+  "recipe": "glm52-v1-bf16",
+  "mode": "mpoa",
+  "attn_layers": [
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40,
+    41,
+    42,
+    43,
+    44,
+    45,
+    46,
+    47,
+    48,
+    49,
+    50,
+    51,
+    52,
+    53,
+    54,
+    55,
+    56,
+    57,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    64,
+    65,
+    66,
+    67,
+    68,
+    69,
+    70,
+    71,
+    72,
+    73,
+    74,
+    75,
+    76,
+    77
+  ],
+  "attn_strength": 4.0,
+  "ffn_layers": [
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40,
+    41,
+    42,
+    43,
+    44,
+    45,
+    46,
+    47,
+    48,
+    49,
+    50,
+    51,
+    52,
+    53,
+    54,
+    55,
+    56,
+    57,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    64,
+    65,
+    66,
+    67,
+    68,
+    69,
+    70,
+    71,
+    72,
+    73,
+    74,
+    75,
+    76,
+    77
+  ],
+  "ffn_strength": 5.0,
+  "n_targets": 119,
+  "change_pct_sample": [
+    [
+      "model.layers.17.self_attn.o_proj.weight",
+      5.24
+    ],
+    [
+      "model.layers.18.self_attn.o_proj.weight",
+      4.83
+    ],
+    [
+      "model.layers.19.self_attn.o_proj.weight",
+      5.66
+    ],
+    [
+      "model.layers.20.self_attn.o_proj.weight",
+      5.34
+    ],
+    [
+      "model.layers.20.mlp.shared_experts.down_proj.weight",
+      4.84
+    ],
+    [
+      "model.layers.21.self_attn.o_proj.weight",
+      6.05
+    ],
+    [
+      "model.layers.21.mlp.shared_experts.down_proj.weight",
+      4.93
+    ],
+    [
+      "model.layers.22.mlp.shared_experts.down_proj.weight",
+      4.67
+    ],
+    [
+      "model.layers.22.self_attn.o_proj.weight",
+      5.02
+    ],
+    [
+      "model.layers.23.self_attn.o_proj.weight",
+      5.25
+    ],
+    [
+      "model.layers.23.mlp.shared_experts.down_proj.weight",
+      6.36
+    ],
+    [
+      "model.layers.24.self_attn.o_proj.weight",
+      4.58
+    ],
+    [
+      "model.layers.24.mlp.shared_experts.down_proj.weight",
+      5.83
+    ],
+    [
+      "model.layers.25.self_attn.o_proj.weight",
+      5.53
+    ],
+    [
+      "model.layers.25.mlp.shared_experts.down_proj.weight",
+      7.19
+    ],
+    [
+      "model.layers.26.self_attn.o_proj.weight",
+      5.26
+    ],
+    [
+      "model.layers.26.mlp.shared_experts.down_proj.weight",
+      6.9
+    ],
+    [
+      "model.layers.27.self_attn.o_proj.weight",
+      4.79
+    ],
+    [
+      "model.layers.27.mlp.shared_experts.down_proj.weight",
+      5.39
+    ],
+    [
+      "model.layers.28.self_attn.o_proj.weight",
+      4.7
+    ],
+    [
+      "model.layers.28.mlp.shared_experts.down_proj.weight",
+      6.4
+    ],
+    [
+      "model.layers.29.self_attn.o_proj.weight",
+      4.98
+    ],
+    [
+      "model.layers.29.mlp.shared_experts.down_proj.weight",
+      6.8
+    ],
+    [
+      "model.layers.30.self_attn.o_proj.weight",
+      4.99
+    ],
+    [
+      "model.layers.30.mlp.shared_experts.down_proj.weight",
+      5.92
+    ],
+    [
+      "model.layers.31.self_attn.o_proj.weight",
+      5.29
+    ],
+    [
+      "model.layers.31.mlp.shared_experts.down_proj.weight",
+      5.45
+    ],
+    [
+      "model.layers.32.self_attn.o_proj.weight",
+      4.77
+    ],
+    [
+      "model.layers.32.mlp.shared_experts.down_proj.weight",
+      6.04
+    ],
+    [
+      "model.layers.33.self_attn.o_proj.weight",
+      4.66
+    ],
+    [
+      "model.layers.33.mlp.shared_experts.down_proj.weight",
+      4.94
+    ],
+    [
+      "model.layers.34.self_attn.o_proj.weight",
+      5.45
+    ],
+    [
+      "model.layers.34.mlp.shared_experts.down_proj.weight",
+      6.23
+    ],
+    [
+      "model.layers.35.self_attn.o_proj.weight",
+      5.44
+    ],
+    [
+      "model.layers.35.mlp.shared_experts.down_proj.weight",
+      5.99
+    ],
+    [
+      "model.layers.36.self_attn.o_proj.weight",
+      5.59
+    ],
+    [
+      "model.layers.36.mlp.shared_experts.down_proj.weight",
+      6.09
+    ],
+    [
+      "model.layers.37.self_attn.o_proj.weight",
+      4.67
+    ],
+    [
+      "model.layers.37.mlp.shared_experts.down_proj.weight",
+      5.66
+    ],
+    [
+      "model.layers.38.self_attn.o_proj.weight",
+      5.29
+    ]
+  ],
+  "change_pct_mean": 6.64
+}

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: dealignai/GLM-5.3-UNCENSORED-FP8
+base_model_relation: quantized
+library_name: exllamav3
+pipeline_tag: text-generation
+tags:
+  - exl3
+  - glm
+  - moe
+  - uncensored
+---
+
+# GLM-5.3-UNCENSORED EXL3 3.0bpw
+
+EXL3 quantization of [dealignai/GLM-5.3-UNCENSORED-FP8](https://huggingface.co/dealignai/GLM-5.3-UNCENSORED-FP8), itself a weight-edited (no fine-tune) variant of [zai-org/GLM-5.3](https://huggingface.co/zai-org/GLM-5.3). The edit is documented in `CRACK_SURGERY.json` (copied unchanged from the source repo). This repo is not affiliated with dealignai or Z.ai.
+
+- Architecture: `GlmMoeDsaForCausalLM`, 753B total parameters, 256 routed experts (8 active) + 1 shared, MLA attention with DSA sparse indexer, 78 layers + 1 MTP layer
+- Average bitrate: 3.04 bpw (`-b 3.0 --hq`; attention and shared experts at 5 bpw, dense MLPs at 4, routed experts at 3), lm_head 6 bpw, `mul1` codebook
+- MTP (next-token prediction) layer included (experts 4 bpw, attention and shared expert 6 bpw, uncalibrated), usable as a speculative draft (`draft_mode: mtp` in TabbyAPI)
+- Size: 273 GiB
+- Converted with ExLlamaV3 at commit `d3739fd`, default calibration (250 rows x 2048 tokens), source read directly from the FP8 checkpoint
+
+## Fidelity vs the FP8 source
+
+`eval/model_diff.py`, 20 rows x 2048 tokens of wikitext-2 test:
+
+| metric | value |
+|---|---|
+| KL divergence (quant ‖ FP8) | 0.089 |
+| KL divergence (FP8 ‖ quant) | 0.097 |
+| per-token KL, median / p90 | 0.021 / 0.221 |
+| perplexity, quant / FP8 | 3.440 / 3.302 |
+| median KL where FP8 top-prob ≥ 0.95 (44% of tokens) | 0.0011 |
+
+## Agentic evaluation
+
+tau2-bench (airline, retail), Pass^1. Agent temperature 1.0, top_p 0.95; user simulator and judges GPT-4.1 at temperature 0. The reference is stock GLM-5.3 (not the uncensored edit) served at FP8 by Z.ai via OpenRouter, run through the same harness. The difference therefore mixes the dealign weight edit and this quantization.
+
+| domain | stock GLM-5.3 FP8 (Z.ai) | this quant | difference |
+|---|---|---|---|
+| airline (50 tasks x 2 trials) | 0.710 ± 0.045 | 0.640 ± 0.048 | -0.070 (~1.1 SE) |
+| retail (114 tasks) | 0.504 ± 0.033 (2 trials) | 0.482 ± 0.047 (1 trial) | -0.022 (~0.4 SE) |
+
+Per trial: airline baseline 0.740 / 0.680, quant 0.600 / 0.680; retail baseline 0.465 / 0.544, quant 0.482. ± is one binomial standard error. Neither difference is statistically significant at these sample sizes; treat the airline point estimate as a possible small regression rather than a measured one.
+
+## Serving
+
+Tested with TabbyAPI on 8x A100 40GB, layer split (`gpu_split_auto`), MTP drafting, 98K-token shared cache.
+
+```yaml
+model:
+  model_name: GLM-5.3-UNCENSORED-EXL3-3.0bpw
+  backend: exllamav3
+  max_seq_len: 65536
+  cache_size: 98304
+  gpu_split_auto: true
+  tool_format: glm4_7
+  reasoning: true
+draft_model:
+  draft_mode: mtp
+```
+
+**Tool calling caveat:** GLM writes tool arguments as raw text (`<arg_value>9523456873</arg_value>`). TabbyAPI's `glm4_5` parser (as of commit `be74bf0`) JSON-decodes every value without consulting the tool schema, so string parameters that look like numbers (order and product IDs, zip codes) reach your tools as integers. On tau2-bench retail this caused ~70% of tool calls to fail. Make the parser keep parameters whose schema type is `string` as raw text before using this model for agents. The evaluation above was run with that fix applied.
+
+## License
+
+MIT, following the upstream GLM-5.3 and dealignai releases.

chat_template.jinja

@@ -0,0 +1,251 @@
+[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 true -%}
+{%- 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 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', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
+                {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
+                {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
+            {%- 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 +1,789 @@
+{
+    "architectures": [
+        "GlmMoeDsaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        154820,
+        154827,
+        154829
+    ],
+    "ep_size": 1,
+    "first_k_dense_replace": 3,
+    "head_dim": 192,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "index_head_dim": 128,
+    "index_n_heads": 32,
+    "index_share_for_mtp_iteration": true,
+    "index_skip_topk_offset": 3,
+    "index_topk": 2048,
+    "index_topk_freq": 4,
+    "index_topk_pattern": null,
+    "indexer_rope_interleave": true,
+    "indexer_types": [
+        "full",
+        "full",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared",
+        "full",
+        "shared",
+        "shared",
+        "shared"
+    ],
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 1048576,
+    "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",
+        "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": "glm_moe_dsa",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "moe_router_dtype": "float32",
+    "n_group": 1,
+    "n_routed_experts": 256,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 78,
+    "num_key_value_heads": 64,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 154820,
+    "pretraining_tp": 1,
+    "q_lora_rank": 2048,
+    "qk_head_dim": 256,
+    "qk_nope_head_dim": 192,
+    "qk_rope_head_dim": 64,
+    "rms_norm_eps": 1e-05,
+    "rope_interleave": true,
+    "rope_parameters": {
+        "rope_theta": 8000000,
+        "rope_type": "default"
+    },
+    "routed_scaling_factor": 2.5,
+    "scoring_func": "sigmoid",
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "transformers_version": "5.15.0",
+    "use_cache": true,
+    "v_head_dim": 256,
+    "vocab_size": 154880,
+    "quantization_config": {
+        "quant_method": "exl3",
+        "version": "1.5.3",
+        "bits": 3.04,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 250,
+            "cols": 2048
+        },
+        "out_scales": "always",
+        "codebook": "mul1",
+        "original_quantization_config": {
+            "activation_scheme": "dynamic",
+            "fmt": "e4m3",
+            "quant_method": "fp8",
+            "weight_block_size": [
+                128,
+                128
+            ],
+            "modules_to_not_convert": [
+                "model.layers.59.post_attention_layernorm",
+                "model.layers.47.mlp.gate.e_score_correction_bias",
+                "model.layers.71.self_attn.kv_a_layernorm",
+                "model.layers.46.mlp.gate.e_score_correction_bias",
+                "model.layers.30.self_attn.kv_a_layernorm",
+                "model.layers.23.self_attn.kv_a_layernorm",
+                "model.layers.73.mlp.gate.e_score_correction_bias",
+                "model.layers.36.mlp.gate",
+                "model.layers.12.self_attn.q_a_layernorm",
+                "model.layers.51.mlp.gate",
+                "model.layers.47.self_attn.kv_a_layernorm",
+                "model.layers.45.self_attn.q_a_layernorm",
+                "model.layers.15.self_attn.q_a_layernorm",
+                "model.layers.39.input_layernorm",
+                "model.layers.50.self_attn.kv_a_layernorm",
+                "model.layers.19.post_attention_layernorm",
+                "model.layers.71.input_layernorm",
+                "model.layers.72.self_attn.kv_a_layernorm",
+                "model.layers.70.mlp.gate",
+                "model.layers.52.input_layernorm",
+                "model.layers.78.self_attn.kv_a_layernorm",
+                "model.layers.48.post_attention_layernorm",
+                "model.layers.4.self_attn.q_a_layernorm",
+                "model.layers.62.self_attn.q_a_layernorm",
+                "model.layers.4.post_attention_layernorm",
+                "model.layers.38.self_attn.indexers_proj",
+                "model.layers.61.mlp.gate.e_score_correction_bias",
+                "model.layers.14.mlp.gate.e_score_correction_bias",
+                "model.layers.36.self_attn.kv_a_layernorm",
+                "model.layers.65.mlp.gate",
+                "model.layers.13.self_attn.kv_a_layernorm",
+                "model.layers.57.mlp.gate",
+                "model.layers.65.self_attn.kv_a_layernorm",
+                "model.layers.68.input_layernorm",
+                "model.layers.70.self_attn.kv_a_layernorm",
+                "model.layers.24.mlp.gate.e_score_correction_bias",
+                "model.layers.4.input_layernorm",
+                "model.layers.20.input_layernorm",
+                "model.layers.65.self_attn.q_a_layernorm",
+                "model.layers.38.mlp.gate",
+                "model.layers.76.mlp.gate.e_score_correction_bias",
+                "model.layers.62.input_layernorm",
+                "model.layers.45.input_layernorm",
+                "model.layers.68.post_attention_layernorm",
+                "model.layers.72.input_layernorm",
+                "model.layers.32.mlp.gate.e_score_correction_bias",
+                "model.layers.27.input_layernorm",
+                "model.layers.16.post_attention_layernorm",
+                "model.layers.35.self_attn.q_a_layernorm",
+                "model.layers.58.self_attn.indexers_proj",
+                "model.layers.3.mlp.gate.e_score_correction_bias",
+                "model.layers.49.self_attn.q_a_layernorm",
+                "model.layers.66.mlp.gate.e_score_correction_bias",
+                "model.layers.10.self_attn.q_a_layernorm",
+                "model.layers.51.mlp.gate.e_score_correction_bias",
+                "model.layers.64.self_attn.q_a_layernorm",
+                "model.layers.70.input_layernorm",
+                "model.layers.71.post_attention_layernorm",
+                "model.layers.67.post_attention_layernorm",
+                "model.layers.6.self_attn.indexer.k_norm",
+                "model.layers.3.mlp.gate",
+                "model.layers.11.mlp.gate",
+                "model.layers.17.input_layernorm",
+                "model.layers.13.mlp.gate",
+                "model.layers.15.mlp.gate",
+                "model.layers.71.self_attn.q_a_layernorm",
+                "model.layers.33.mlp.gate.e_score_correction_bias",
+                "model.layers.72.mlp.gate.e_score_correction_bias",
+                "model.layers.65.post_attention_layernorm",
+                "model.layers.78.hnorm",
+                "model.layers.40.post_attention_layernorm",
+                "model.layers.12.mlp.gate.e_score_correction_bias",
+                "model.layers.8.input_layernorm",
+                "model.layers.73.mlp.gate",
+                "model.layers.11.post_attention_layernorm",
+                "model.layers.61.input_layernorm",
+                "model.layers.14.self_attn.kv_a_layernorm",
+                "model.layers.39.self_attn.kv_a_layernorm",
+                "model.layers.70.self_attn.indexer.k_norm",
+                "model.layers.45.mlp.gate",
+                "model.layers.51.self_attn.q_a_layernorm",
+                "model.layers.64.post_attention_layernorm",
+                "model.layers.20.post_attention_layernorm",
+                "model.layers.66.self_attn.kv_a_layernorm",
+                "model.layers.10.self_attn.indexer.k_norm.bias",
+                "model.layers.23.input_layernorm",
+                "model.layers.38.self_attn.indexer.k_norm",
+                "model.layers.19.self_attn.kv_a_layernorm",
+                "model.layers.40.self_attn.q_a_layernorm",
+                "model.layers.10.self_attn.indexer.k_norm",
+                "model.layers.44.post_attention_layernorm",
+                "model.layers.70.post_attention_layernorm",
+                "model.layers.41.mlp.gate.e_score_correction_bias",
+                "model.layers.36.post_attention_layernorm",
+                "model.layers.30.self_attn.indexer.k_norm.bias",
+                "model.layers.54.self_attn.q_a_layernorm",
+                "model.layers.59.mlp.gate",
+                "model.layers.69.post_attention_layernorm",
+                "lm_head",
+                "model.layers.77.self_attn.kv_a_layernorm",
+                "model.layers.75.self_attn.q_a_layernorm",
+                "model.layers.56.self_attn.q_a_layernorm",
+                "model.layers.50.self_attn.indexer.k_norm.bias",
+                "model.layers.54.mlp.gate",
+                "model.layers.6.self_attn.indexer.k_norm.bias",
+                "model.layers.15.input_layernorm",
+                "model.layers.29.self_attn.q_a_layernorm",
+                "model.layers.54.self_attn.indexers_proj",
+                "model.layers.73.self_attn.kv_a_layernorm",
+                "model.layers.0.self_attn.indexer.k_norm",
+                "model.layers.58.self_attn.indexer.k_norm",
+                "model.layers.36.input_layernorm",
+                "model.layers.47.self_attn.q_a_layernorm",
+                "model.layers.26.mlp.gate.e_score_correction_bias",
+                "model.layers.50.input_layernorm",
+                "model.layers.16.self_attn.q_a_layernorm",
+                "model.layers.19.mlp.gate.e_score_correction_bias",
+                "model.layers.78.input_layernorm",
+                "model.layers.27.mlp.gate",
+                "model.layers.19.self_attn.q_a_layernorm",
+                "model.layers.25.input_layernorm",
+                "model.layers.33.self_attn.kv_a_layernorm",
+                "model.layers.32.mlp.gate",
+                "model.layers.61.self_attn.kv_a_layernorm",
+                "model.layers.50.self_attn.indexers_proj",
+                "model.layers.34.self_attn.indexers_proj",
+                "model.layers.4.mlp.gate.e_score_correction_bias",
+                "model.layers.76.post_attention_layernorm",
+                "model.layers.57.post_attention_layernorm",
+                "model.layers.73.post_attention_layernorm",
+                "model.layers.68.mlp.gate.e_score_correction_bias",
+                "model.layers.34.self_attn.kv_a_layernorm",
+                "model.layers.78.enorm",
+                "model.layers.30.mlp.gate",
+                "model.layers.10.self_attn.indexers_proj",
+                "model.layers.34.input_layernorm",
+                "model.layers.34.post_attention_layernorm",
+                "model.layers.20.mlp.gate.e_score_correction_bias",
+                "model.layers.54.self_attn.indexer.k_norm.bias",
+                "model.layers.44.mlp.gate",
+                "model.layers.25.mlp.gate.e_score_correction_bias",
+                "model.layers.26.self_attn.indexers_proj",
+                "model.layers.66.self_attn.indexer.k_norm.bias",
+                "model.layers.41.post_attention_layernorm",
+                "model.layers.51.post_attention_layernorm",
+                "model.layers.22.self_attn.indexer.k_norm.bias",
+                "model.layers.21.mlp.gate.e_score_correction_bias",
+                "model.layers.15.self_attn.kv_a_layernorm",
+                "model.layers.25.self_attn.kv_a_layernorm",
+                "model.layers.55.mlp.gate",
+                "model.layers.11.self_attn.q_a_layernorm",
+                "model.layers.72.mlp.gate",
+                "model.layers.21.self_attn.kv_a_layernorm",
+                "model.layers.59.mlp.gate.e_score_correction_bias",
+                "model.layers.2.input_layernorm",
+                "model.layers.5.mlp.gate",
+                "model.layers.54.self_attn.kv_a_layernorm",
+                "model.layers.0.self_attn.indexers_proj",
+                "model.layers.71.mlp.gate.e_score_correction_bias",
+                "model.layers.6.self_attn.q_a_layernorm",
+                "model.layers.14.mlp.gate",
+                "model.layers.44.self_attn.kv_a_layernorm",
+                "model.layers.61.post_attention_layernorm",
+                "model.layers.64.self_attn.kv_a_layernorm",
+                "model.layers.1.post_attention_layernorm",
+                "model.layers.4.mlp.gate",
+                "model.layers.22.post_attention_layernorm",
+                "model.layers.21.self_attn.q_a_layernorm",
+                "model.layers.74.self_attn.q_a_layernorm",
+                "model.layers.18.self_attn.indexers_proj",
+                "model.layers.75.input_layernorm",
+                "model.layers.70.self_attn.q_a_layernorm",
+                "model.layers.22.self_attn.indexer.k_norm",
+                "model.layers.42.mlp.gate.e_score_correction_bias",
+                "model.layers.5.self_attn.kv_a_layernorm",
+                "model.layers.31.mlp.gate.e_score_correction_bias",
+                "model.layers.62.self_attn.indexer.k_norm.bias",
+                "model.layers.29.post_attention_layernorm",
+                "model.layers.6.self_attn.kv_a_layernorm",
+                "model.layers.48.input_layernorm",
+                "model.layers.74.self_attn.indexer.k_norm.bias",
+                "model.layers.7.input_layernorm",
+                "model.layers.39.self_attn.q_a_layernorm",
+                "model.layers.41.input_layernorm",
+                "model.layers.54.self_attn.indexer.k_norm",
+                "model.layers.32.self_attn.q_a_layernorm",
+                "model.layers.39.mlp.gate.e_score_correction_bias",
+                "model.layers.42.input_layernorm",
+                "model.layers.43.mlp.gate",
+                "model.layers.72.self_attn.q_a_layernorm",
+                "model.layers.37.mlp.gate.e_score_correction_bias",
+                "model.layers.5.post_attention_layernorm",
+                "model.layers.28.mlp.gate",
+                "model.layers.2.post_attention_layernorm",
+                "model.layers.49.post_attention_layernorm",
+                "model.layers.43.self_attn.kv_a_layernorm",
+                "model.layers.12.input_layernorm",
+                "model.layers.56.mlp.gate",
+                "model.layers.5.input_layernorm",
+                "model.layers.29.mlp.gate.e_score_correction_bias",
+                "model.layers.4.self_attn.kv_a_layernorm",
+                "model.layers.20.self_attn.q_a_layernorm",
+                "model.layers.59.self_attn.q_a_layernorm",
+                "model.layers.68.mlp.gate",
+                "model.layers.21.post_attention_layernorm",
+                "model.layers.26.self_attn.q_a_layernorm",
+                "model.layers.52.self_attn.q_a_layernorm",
+                "model.layers.29.self_attn.kv_a_layernorm",
+                "model.layers.24.input_layernorm",
+                "model.layers.34.self_attn.indexer.k_norm.bias",
+                "model.layers.43.input_layernorm",
+                "model.layers.27.self_attn.kv_a_layernorm",
+                "model.layers.31.input_layernorm",
+                "model.layers.69.mlp.gate",
+                "model.layers.26.post_attention_layernorm",
+                "model.layers.3.self_attn.q_a_layernorm",
+                "model.layers.37.post_attention_layernorm",
+                "model.layers.52.mlp.gate",
+                "model.layers.73.input_layernorm",
+                "model.layers.19.input_layernorm",
+                "model.layers.13.self_attn.q_a_layernorm",
+                "model.layers.76.input_layernorm",
+                "model.layers.8.mlp.gate",
+                "model.layers.63.post_attention_layernorm",
+                "model.layers.58.mlp.gate",
+                "model.layers.31.post_attention_layernorm",
+                "model.layers.23.mlp.gate.e_score_correction_bias",
+                "model.layers.34.self_attn.q_a_layernorm",
+                "model.layers.78.self_attn.indexer.k_norm.bias",
+                "model.layers.13.mlp.gate.e_score_correction_bias",
+                "model.layers.71.mlp.gate",
+                "model.layers.14.input_layernorm",
+                "model.layers.17.mlp.gate.e_score_correction_bias",
+                "model.layers.8.post_attention_layernorm",
+                "model.layers.45.self_attn.kv_a_layernorm",
+                "model.layers.46.self_attn.indexer.k_norm",
+                "model.layers.20.self_attn.kv_a_layernorm",
+                "model.layers.78.self_attn.indexer.k_norm",
+                "model.layers.37.mlp.gate",
+                "model.layers.7.mlp.gate",
+                "model.layers.30.mlp.gate.e_score_correction_bias",
+                "model.layers.67.mlp.gate",
+                "model.layers.73.self_attn.q_a_layernorm",
+                "model.layers.10.self_attn.kv_a_layernorm",
+                "model.layers.61.mlp.gate",
+                "model.layers.22.mlp.gate.e_score_correction_bias",
+                "model.layers.58.input_layernorm",
+                "model.layers.8.self_attn.kv_a_layernorm",
+                "model.layers.33.self_attn.q_a_layernorm",
+                "model.layers.55.self_attn.q_a_layernorm",
+                "model.layers.32.input_layernorm",
+                "model.layers.17.self_attn.kv_a_layernorm",
+                "model.layers.46.self_attn.indexer.k_norm.bias",
+                "model.layers.11.mlp.gate.e_score_correction_bias",
+                "model.layers.9.input_layernorm",
+                "model.layers.77.input_layernorm",
+                "model.layers.16.self_attn.kv_a_layernorm",
+                "model.layers.45.post_attention_layernorm",
+                "model.layers.74.mlp.gate",
+                "model.layers.68.self_attn.q_a_layernorm",
+                "model.layers.55.self_attn.kv_a_layernorm",
+                "model.layers.44.input_layernorm",
+                "model.layers.60.self_attn.kv_a_layernorm",
+                "model.layers.14.post_attention_layernorm",
+                "model.layers.62.self_attn.indexers_proj",
+                "model.layers.0.self_attn.q_a_layernorm",
+                "model.layers.72.post_attention_layernorm",
+                "model.layers.78.post_attention_layernorm",
+                "model.layers.60.mlp.gate.e_score_correction_bias",
+                "model.layers.26.self_attn.indexer.k_norm.bias",
+                "model.layers.38.post_attention_layernorm",
+                "model.layers.50.post_attention_layernorm",
+                "model.layers.28.input_layernorm",
+                "model.layers.30.self_attn.indexer.k_norm",
+                "model.layers.37.self_attn.q_a_layernorm",
+                "model.layers.56.input_layernorm",
+                "model.layers.27.post_attention_layernorm",
+                "model.layers.74.input_layernorm",
+                "model.layers.78.self_attn.q_a_layernorm",
+                "model.layers.42.self_attn.q_a_layernorm",
+                "model.layers.26.self_attn.indexer.k_norm",
+                "model.layers.42.self_attn.kv_a_layernorm",
+                "model.layers.1.self_attn.indexer.k_norm",
+                "model.layers.39.post_attention_layernorm",
+                "model.layers.48.mlp.gate.e_score_correction_bias",
+                "model.layers.74.post_attention_layernorm",
+                "model.layers.69.self_attn.q_a_layernorm",
+                "model.layers.13.input_layernorm",
+                "model.layers.74.self_attn.indexer.k_norm",
+                "model.layers.29.mlp.gate",
+                "model.layers.7.mlp.gate.e_score_correction_bias",
+                "model.layers.3.self_attn.kv_a_layernorm",
+                "model.layers.35.self_attn.kv_a_layernorm",
+                "model.layers.46.self_attn.indexers_proj",
+                "model.layers.0.self_attn.kv_a_layernorm",
+                "model.layers.43.self_attn.q_a_layernorm",
+                "model.norm",
+                "model.layers.1.self_attn.kv_a_layernorm",
+                "model.layers.38.self_attn.indexer.k_norm.bias",
+                "model.layers.30.self_attn.q_a_layernorm",
+                "model.layers.0.input_layernorm",
+                "model.layers.47.input_layernorm",
+                "model.layers.8.self_attn.q_a_layernorm",
+                "model.layers.61.self_attn.q_a_layernorm",
+                "model.layers.1.self_attn.indexer.k_norm.bias",
+                "model.layers.62.mlp.gate.e_score_correction_bias",
+                "model.layers.66.self_attn.q_a_layernorm",
+                "model.layers.46.self_attn.kv_a_layernorm",
+                "model.layers.66.mlp.gate",
+                "model.layers.69.input_layernorm",
+                "model.layers.69.self_attn.kv_a_layernorm",
+                "model.layers.22.input_layernorm",
+                "model.layers.30.post_attention_layernorm",
+                "model.layers.24.self_attn.q_a_layernorm",
+                "model.layers.48.mlp.gate",
+                "model.layers.7.self_attn.kv_a_layernorm",
+                "model.layers.67.input_layernorm",
+                "model.layers.27.self_attn.q_a_layernorm",
+                "model.layers.23.mlp.gate",
+                "model.layers.45.mlp.gate.e_score_correction_bias",
+                "model.layers.76.self_attn.kv_a_layernorm",
+                "model.layers.22.self_attn.q_a_layernorm",
+                "model.layers.78.mlp.gate",
+                "model.layers.9.mlp.gate",
+                "model.layers.57.self_attn.q_a_layernorm",
+                "model.layers.78.mlp.gate.e_score_correction_bias",
+                "model.layers.23.post_attention_layernorm",
+                "model.layers.38.self_attn.q_a_layernorm",
+                "model.layers.53.mlp.gate",
+                "model.layers.77.self_attn.q_a_layernorm",
+                "model.layers.62.self_attn.kv_a_layernorm",
+                "model.layers.12.mlp.gate",
+                "model.layers.34.self_attn.indexer.k_norm",
+                "model.layers.46.self_attn.q_a_layernorm",
+                "model.layers.36.self_attn.q_a_layernorm",
+                "model.layers.58.self_attn.indexer.k_norm.bias",
+                "model.layers.60.post_attention_layernorm",
+                "model.layers.28.post_attention_layernorm",
+                "model.layers.2.self_attn.kv_a_layernorm",
+                "model.layers.70.self_attn.indexers_proj",
+                "model.layers.16.mlp.gate.e_score_correction_bias",
+                "model.layers.2.self_attn.indexer.k_norm",
+                "model.layers.31.self_attn.kv_a_layernorm",
+                "model.layers.64.input_layernorm",
+                "model.layers.6.mlp.gate.e_score_correction_bias",
+                "model.layers.50.self_attn.indexer.k_norm",
+                "model.layers.58.self_attn.q_a_layernorm",
+                "model.layers.57.mlp.gate.e_score_correction_bias",
+                "model.layers.13.post_attention_layernorm",
+                "model.layers.28.self_attn.kv_a_layernorm",
+                "model.layers.31.self_attn.q_a_layernorm",
+                "model.layers.1.self_attn.q_a_layernorm",
+                "model.layers.17.mlp.gate",
+                "model.layers.15.post_attention_layernorm",
+                "model.layers.18.self_attn.indexer.k_norm.bias",
+                "model.layers.18.self_attn.indexer.k_norm",
+                "model.layers.43.mlp.gate.e_score_correction_bias",
+                "model.layers.11.input_layernorm",
+                "model.layers.9.post_attention_layernorm",
+                "model.layers.33.input_layernorm",
+                "model.layers.66.input_layernorm",
+                "model.layers.78.self_attn.indexers_proj",
+                "model.layers.54.post_attention_layernorm",
+                "model.layers.53.mlp.gate.e_score_correction_bias",
+                "model.layers.5.mlp.gate.e_score_correction_bias",
+                "model.layers.19.mlp.gate",
+                "model.layers.49.mlp.gate",
+                "model.layers.66.self_attn.indexers_proj",
+                "model.layers.14.self_attn.indexer.k_norm.bias",
+                "model.layers.41.mlp.gate",
+                "model.layers.42.self_attn.indexer.k_norm.bias",
+                "model.layers.65.input_layernorm",
+                "model.layers.75.mlp.gate",
+                "model.layers.12.self_attn.kv_a_layernorm",
+                "model.layers.53.input_layernorm",
+                "model.layers.58.self_attn.kv_a_layernorm",
+                "model.layers.60.self_attn.q_a_layernorm",
+                "model.layers.6.mlp.gate",
+                "model.layers.49.self_attn.kv_a_layernorm",
+                "model.layers.16.mlp.gate",
+                "model.layers.22.mlp.gate",
+                "model.layers.58.post_attention_layernorm",
+                "model.layers.15.mlp.gate.e_score_correction_bias",
+                "model.layers.26.input_layernorm",
+                "model.layers.3.post_attention_layernorm",
+                "model.layers.6.input_layernorm",
+                "model.layers.22.self_attn.kv_a_layernorm",
+                "model.layers.16.input_layernorm",
+                "model.layers.33.post_attention_layernorm",
+                "model.layers.17.post_attention_layernorm",
+                "model.layers.35.mlp.gate",
+                "model.layers.56.post_attention_layernorm",
+                "model.layers.7.self_attn.q_a_layernorm",
+                "model.layers.24.mlp.gate",
+                "model.layers.24.post_attention_layernorm",
+                "model.layers.36.mlp.gate.e_score_correction_bias",
+                "model.layers.56.mlp.gate.e_score_correction_bias",
+                "model.layers.32.post_attention_layernorm",
+                "model.layers.47.post_attention_layernorm",
+                "model.layers.40.mlp.gate",
+                "model.layers.41.self_attn.kv_a_layernorm",
+                "model.layers.52.self_attn.kv_a_layernorm",
+                "model.layers.9.self_attn.kv_a_layernorm",
+                "model.layers.77.mlp.gate.e_score_correction_bias",
+                "model.layers.78.shared_head.norm",
+                "model.layers.53.post_attention_layernorm",
+                "model.layers.63.self_attn.kv_a_layernorm",
+                "model.layers.48.self_attn.kv_a_layernorm",
+                "model.layers.28.mlp.gate.e_score_correction_bias",
+                "model.layers.8.mlp.gate.e_score_correction_bias",
+                "model.layers.52.mlp.gate.e_score_correction_bias",
+                "model.layers.52.post_attention_layernorm",
+                "model.layers.18.self_attn.q_a_layernorm",
+                "model.layers.50.mlp.gate.e_score_correction_bias",
+                "model.layers.64.mlp.gate.e_score_correction_bias",
+                "model.layers.38.mlp.gate.e_score_correction_bias",
+                "model.layers.59.input_layernorm",
+                "model.layers.21.input_layernorm",
+                "model.layers.39.mlp.gate",
+                "model.layers.77.post_attention_layernorm",
+                "model.layers.76.self_attn.q_a_layernorm",
+                "model.layers.12.post_attention_layernorm",
+                "model.layers.43.post_attention_layernorm",
+                "model.layers.35.input_layernorm",
+                "model.layers.62.mlp.gate",
+                "model.layers.38.self_attn.kv_a_layernorm",
+                "model.layers.63.mlp.gate",
+                "model.layers.27.mlp.gate.e_score_correction_bias",
+                "model.layers.18.mlp.gate",
+                "model.layers.25.post_attention_layernorm",
+                "model.layers.55.mlp.gate.e_score_correction_bias",
+                "model.layers.66.self_attn.indexer.k_norm",
+                "model.layers.48.self_attn.q_a_layernorm",
+                "model.layers.78.eh_proj",
+                "model.layers.77.mlp.gate",
+                "model.layers.6.self_attn.indexers_proj",
+                "model.layers.14.self_attn.q_a_layernorm",
+                "model.layers.2.self_attn.q_a_layernorm",
+                "model.layers.42.mlp.gate",
+                "model.layers.54.mlp.gate.e_score_correction_bias",
+                "model.layers.60.input_layernorm",
+                "model.layers.40.self_attn.kv_a_layernorm",
+                "model.layers.51.self_attn.kv_a_layernorm",
+                "model.layers.18.input_layernorm",
+                "model.layers.30.self_attn.indexers_proj",
+                "model.layers.53.self_attn.kv_a_layernorm",
+                "model.layers.6.post_attention_layernorm",
+                "model.layers.70.self_attn.indexer.k_norm.bias",
+                "model.layers.54.input_layernorm",
+                "model.layers.41.self_attn.q_a_layernorm",
+                "model.layers.18.mlp.gate.e_score_correction_bias",
+                "model.layers.34.mlp.gate.e_score_correction_bias",
+                "model.layers.47.mlp.gate",
+                "model.layers.46.mlp.gate",
+                "model.layers.25.self_attn.q_a_layernorm",
+                "model.layers.63.mlp.gate.e_score_correction_bias",
+                "model.layers.66.post_attention_layernorm",
+                "model.layers.76.mlp.gate",
+                "model.embed_tokens",
+                "model.layers.67.self_attn.kv_a_layernorm",
+                "model.layers.67.mlp.gate.e_score_correction_bias",
+                "model.layers.26.self_attn.kv_a_layernorm",
+                "model.layers.31.mlp.gate",
+                "model.layers.18.self_attn.kv_a_layernorm",
+                "model.layers.34.mlp.gate",
+                "model.layers.55.post_attention_layernorm",
+                "model.layers.30.input_layernorm",
+                "model.layers.50.mlp.gate",
+                "model.layers.63.input_layernorm",
+                "model.layers.11.self_attn.kv_a_layernorm",
+                "model.layers.24.self_attn.kv_a_layernorm",
+                "model.layers.75.mlp.gate.e_score_correction_bias",
+                "model.layers.10.post_attention_layernorm",
+                "model.layers.1.self_attn.indexers_proj",
+                "model.layers.42.self_attn.indexers_proj",
+                "model.layers.46.input_layernorm",
+                "model.layers.23.self_attn.q_a_layernorm",
+                "model.layers.63.self_attn.q_a_layernorm",
+                "model.layers.14.self_attn.indexer.k_norm",
+                "model.layers.14.self_attn.indexers_proj",
+                "model.layers.60.mlp.gate",
+                "model.layers.70.mlp.gate.e_score_correction_bias",
+                "model.layers.53.self_attn.q_a_layernorm",
+                "model.layers.0.post_attention_layernorm",
+                "model.layers.35.mlp.gate.e_score_correction_bias",
+                "model.layers.75.self_attn.kv_a_layernorm",
+                "model.layers.1.input_layernorm",
+                "model.layers.42.post_attention_layernorm",
+                "model.layers.37.input_layernorm",
+                "model.layers.9.mlp.gate.e_score_correction_bias",
+                "model.layers.46.post_attention_layernorm",
+                "model.layers.26.mlp.gate",
+                "model.layers.65.mlp.gate.e_score_correction_bias",
+                "model.layers.67.self_attn.q_a_layernorm",
+                "model.layers.44.mlp.gate.e_score_correction_bias",
+                "model.layers.33.mlp.gate",
+                "model.layers.29.input_layernorm",
+                "model.layers.18.post_attention_layernorm",
+                "model.layers.75.post_attention_layernorm",
+                "model.layers.44.self_attn.q_a_layernorm",
+                "model.layers.10.mlp.gate",
+                "model.layers.21.mlp.gate",
+                "model.layers.58.mlp.gate.e_score_correction_bias",
+                "model.layers.7.post_attention_layernorm",
+                "model.layers.50.self_attn.q_a_layernorm",
+                "model.layers.9.self_attn.q_a_layernorm",
+                "model.layers.2.self_attn.indexers_proj",
+                "model.layers.0.self_attn.indexer.k_norm.bias",
+                "model.layers.74.self_attn.kv_a_layernorm",
+                "model.layers.74.mlp.gate.e_score_correction_bias",
+                "model.layers.49.mlp.gate.e_score_correction_bias",
+                "model.layers.62.post_attention_layernorm",
+                "model.layers.57.self_attn.kv_a_layernorm",
+                "model.layers.40.input_layernorm",
+                "model.layers.69.mlp.gate.e_score_correction_bias",
+                "model.layers.35.post_attention_layernorm",
+                "model.layers.74.self_attn.indexers_proj",
+                "model.layers.55.input_layernorm",
+                "model.layers.49.input_layernorm",
+                "model.layers.40.mlp.gate.e_score_correction_bias",
+                "model.layers.25.mlp.gate",
+                "model.layers.2.self_attn.indexer.k_norm.bias",
+                "model.layers.68.self_attn.kv_a_layernorm",
+                "model.layers.51.input_layernorm",
+                "model.layers.22.self_attn.indexers_proj",
+                "model.layers.10.input_layernorm",
+                "model.layers.42.self_attn.indexer.k_norm",
+                "model.layers.56.self_attn.kv_a_layernorm",
+                "model.layers.17.self_attn.q_a_layernorm",
+                "model.layers.59.self_attn.kv_a_layernorm",
+                "model.layers.3.input_layernorm",
+                "model.layers.57.input_layernorm",
+                "model.layers.38.input_layernorm",
+                "model.layers.62.self_attn.indexer.k_norm",
+                "model.layers.20.mlp.gate",
+                "model.layers.64.mlp.gate",
+                "model.layers.28.self_attn.q_a_layernorm",
+                "model.layers.32.self_attn.kv_a_layernorm",
+                "model.layers.10.mlp.gate.e_score_correction_bias",
+                "model.layers.5.self_attn.q_a_layernorm",
+                "model.layers.37.self_attn.kv_a_layernorm"
+            ]
+        },
+        "mtp_bits": 4
+    }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.12.0",
+  "repetition_penalty": 1.1
+}

model-00001-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694ff2362fa912cf64f257e92c0aec9a954529e6affb3cfef096bb4b145b2521
+size 6423373049

model-00002-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f20a9e54aee32420815a6e15be283f211a34a74f360524d0273867a8e4cdc07
+size 7574655594

model-00003-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d507a99408b8d767880412deaac6f9f273c87bd151288f1619757b7e9a63f2
+size 7581878302

model-00004-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529b1bd1131a64ba44712b3e18a260e0e7e482f636a9a09b04a020bbdfa16d88
+size 7574655594

model-00005-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8f25d93f8de8872c4e851d4c1e40a606a0c0a8861d8a72b225f70a6d614da2
+size 7581884524

model-00006-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e019401b928629680672032fd9806d5d11c52020f502760aac4785427a86a1
+size 7574661808

model-00007-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af55a61d5d01f29d4dece1e4a6a715245d94061bbf9ee8af3b5e7bbb0c69d2b
+size 7581884524

model-00008-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e904b89fbbd6b50f0b2070ad4bf767f24076ea2ff1beb89aaafa0da24ce9af
+size 7574661808

model-00009-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4dd725b167e8499b73d60cf3a89159e00673ccd96c38314314e508c94d30e09
+size 7581884524

model-00010-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b771bcdd8152574499e9b4149d7639d843f24b431952d0eac93720ca373400
+size 7574661808

model-00011-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17418913111f315432efa076a7c7014788fbfca4e670fbcce2beef70d889131c
+size 7581884524

model-00012-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49016e7a861347662d9d6976911214119ab0b1c9f7e35fa181aacd8a5fe221e
+size 7574661808

model-00013-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125506b241ce4704237940df12aa45a563e2d4ee5d9a84e9bdf84000d36f48c0
+size 7581884524

model-00014-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddd95919be6a435e0091b087d572361e56f2caebd166e6b54d97cb49310dc3b
+size 7574661808

model-00015-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba2982791d2dbb1db2dd213a0529ca7a3f49cf488f37dca079811a2742d62dd7
+size 7581884524

model-00016-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9d7fdc682a45c69b4b19c370b00f15b5b49307e15299297a78ca34862fd92f
+size 7574661808

model-00017-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f722efd1a906510f71c06dfba83e0aae2adfb409e167b6ddbd04841615feb940
+size 7581884524

model-00018-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8f6064979b4438353a31fd4c3b3eb683aaede31657c67e4627bc0ff8211d79
+size 7574661808

model-00019-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2b138171d4e08a365b637024310a1090e8bd20d2dafa2ea2ceecd1b3019298
+size 7581884524

model-00020-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8706fab5670e7964b2ad9dbccf361cc18cd1b5fd36eb46feed687b410ff06ab4
+size 7574661808

model-00021-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590ff4032fb9022075b5b817b41b8fb0d346d0843b3a4556532859b6668b580d
+size 7581884524

model-00022-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3028ace572d44930e0e9b6ad38233b412bba6d60392e6117a15a833c44a8e874
+size 7574661808

model-00023-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66279938c3b6d23965e8ec0fc79c3248674d9e15f9cb0de244643fe1106d0815
+size 7581884524

model-00024-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8feeafc8dcda71e4baf179a25abfae27581c93b865e2ac00076081a536cac7
+size 7574661808

model-00025-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de455f051eaa4190402e3c8fd3de1a6bf62263730d6edad5a3a78e6be03fe48f
+size 7581884524

model-00026-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1daa77e12b52edf9490806c1dcc432c3e9a17e9d376b968d5f819260b8165ef7
+size 7574661808

model-00027-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f72940f379aabff74a0177585bb4d352317fe0c42c1ef32b3e27b7dbdfc0171
+size 7581884524

model-00028-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e0c7d0234a88d65253a332113523ea487cc2a638fc44137152cb99b3a31a46
+size 7574661808

model-00029-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac95509af4eb0d85abf366940de7b50e4392e95d87ef8ce1a6e5fa749263966
+size 7581884524

model-00030-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23dcdad8f27033de05acb04bdc33a02d182ddcc973b5c3ef51ad422a80abd1a7
+size 7574661808

model-00031-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82faa1df1164051da47f0cf10b91d1b1f8ac5f7bc8e9eeae9f0fd7b06ed17e7
+size 7581884524

model-00032-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2656e001e8025dd9e660a3b62297e819499bb40df288798bd62350ea46f228e7
+size 7574661808

model-00033-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecbebbdf714de5d98429e26893d11263d71b94b364368cd8d023c7943edc7fb
+size 7581884524

model-00034-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753371268147dbc47a12b036306d3e4c42feeb80e11974795ddcaea5e8752727
+size 7574661808

model-00035-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad55573293336e72dc21c827bd0dc51108d51c3194f3b30dc52deb9bc3e36754
+size 7581884524

model-00036-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2875cfcbdf7be2266497767956eeec6b978e928c78ca7441a8724f4c04ca28
+size 7574661808

model-00037-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2623ad834dfc3b90e78f3c809261a6e1a8d6ec3d92dc51a7de25e87dbd1fa0a9
+size 7581884524

model-00038-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880b05c452bbdd4953967bdac3bdd39293f5ce087c3973bf174a74aab8ee4fe5
+size 8335931601

model-00039-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a43fa0962ebe891c668a9ef458259376d2f6af81c9d4591fdf650bb6103403
+size 5074381845

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b617a0253f2ef57c3aad12deaa8e710b661e611278640cff85c06d2f3537c46
+size 21997762

quantization_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830b50a8708ded28aee3ce0aa59cf53c02d6cd27e384da7bb5d9bb4bb7773727
+size 71764377

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
+size 20217442

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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,
+  "model_max_length": 1048576,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}