Duplicate from dealignai/GLM-5.3-CYBERSECURITY-FP8

Co-authored-by: dealign.ai <dealignai@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

CRACK_SURGERY.json

@@ -0,0 +1,310 @@
+{
+  "recipe": "glm52-v1-bf16",
+  "mode": "mpoa",
+  "attn_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    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": 124,
+  "change_pct_sample": [
+    [
+      "model.layers.12.self_attn.o_proj.weight",
+      5.2
+    ],
+    [
+      "model.layers.13.self_attn.o_proj.weight",
+      4.73
+    ],
+    [
+      "model.layers.14.self_attn.o_proj.weight",
+      5.98
+    ],
+    [
+      "model.layers.15.self_attn.o_proj.weight",
+      4.51
+    ],
+    [
+      "model.layers.16.self_attn.o_proj.weight",
+      5.56
+    ],
+    [
+      "model.layers.17.self_attn.o_proj.weight",
+      5.06
+    ],
+    [
+      "model.layers.18.self_attn.o_proj.weight",
+      4.7
+    ],
+    [
+      "model.layers.19.self_attn.o_proj.weight",
+      5.11
+    ],
+    [
+      "model.layers.20.self_attn.o_proj.weight",
+      5.19
+    ],
+    [
+      "model.layers.20.mlp.shared_experts.down_proj.weight",
+      5.68
+    ],
+    [
+      "model.layers.21.self_attn.o_proj.weight",
+      5.68
+    ],
+    [
+      "model.layers.21.mlp.shared_experts.down_proj.weight",
+      5.4
+    ],
+    [
+      "model.layers.22.mlp.shared_experts.down_proj.weight",
+      5.07
+    ],
+    [
+      "model.layers.22.self_attn.o_proj.weight",
+      4.85
+    ],
+    [
+      "model.layers.23.self_attn.o_proj.weight",
+      5.54
+    ],
+    [
+      "model.layers.23.mlp.shared_experts.down_proj.weight",
+      6.3
+    ],
+    [
+      "model.layers.24.self_attn.o_proj.weight",
+      4.64
+    ],
+    [
+      "model.layers.24.mlp.shared_experts.down_proj.weight",
+      5.98
+    ],
+    [
+      "model.layers.25.self_attn.o_proj.weight",
+      5.3
+    ],
+    [
+      "model.layers.25.mlp.shared_experts.down_proj.weight",
+      6.74
+    ],
+    [
+      "model.layers.26.self_attn.o_proj.weight",
+      5.17
+    ],
+    [
+      "model.layers.26.mlp.shared_experts.down_proj.weight",
+      6.55
+    ],
+    [
+      "model.layers.27.self_attn.o_proj.weight",
+      5.08
+    ],
+    [
+      "model.layers.27.mlp.shared_experts.down_proj.weight",
+      5.3
+    ],
+    [
+      "model.layers.28.self_attn.o_proj.weight",
+      4.62
+    ],
+    [
+      "model.layers.28.mlp.shared_experts.down_proj.weight",
+      6.4
+    ],
+    [
+      "model.layers.29.self_attn.o_proj.weight",
+      5.11
+    ],
+    [
+      "model.layers.29.mlp.shared_experts.down_proj.weight",
+      6.92
+    ],
+    [
+      "model.layers.30.self_attn.o_proj.weight",
+      5.1
+    ],
+    [
+      "model.layers.30.mlp.shared_experts.down_proj.weight",
+      6.22
+    ],
+    [
+      "model.layers.31.self_attn.o_proj.weight",
+      5.12
+    ],
+    [
+      "model.layers.31.mlp.shared_experts.down_proj.weight",
+      6.01
+    ],
+    [
+      "model.layers.32.self_attn.o_proj.weight",
+      6.24
+    ],
+    [
+      "model.layers.32.mlp.shared_experts.down_proj.weight",
+      6.98
+    ],
+    [
+      "model.layers.33.self_attn.o_proj.weight",
+      4.96
+    ],
+    [
+      "model.layers.33.mlp.shared_experts.down_proj.weight",
+      5.79
+    ],
+    [
+      "model.layers.34.self_attn.o_proj.weight",
+      5.51
+    ],
+    [
+      "model.layers.34.mlp.shared_experts.down_proj.weight",
+      6.65
+    ],
+    [
+      "model.layers.35.self_attn.o_proj.weight",
+      6.68
+    ],
+    [
+      "model.layers.35.mlp.shared_experts.down_proj.weight",
+      6.53
+    ]
+  ],
+  "change_pct_mean": 8.19
+}

README.md

@@ -0,0 +1,181 @@
+---
+license: mit
+base_model:
+- zai-org/GLM-5.3
+- JANGQ-AI/GLM-5.3-FP8
+language:
+- en
+- zh
+- ru
+- sr
+- hi
+- fr
+- es
+- ar
+- ko
+- ja
+tags:
+- abliterated
+- crack
+- refusal-removed
+- domain-specific
+- cybersecurity
+- offensive-security
+- red-team
+- pentest
+- glm
+- moe
+- fp8
+- glm_moe_dsa
+thumbnail: dealign_mascot.png
+pipeline_tag: text-generation
+---
+
+<div align="center">
+
+<img src="dealign_mascot.png" width="160" alt="dealignai mascot" />
+
+# GLM 5.3 CRACK — Cybersecurity FP8
+
+**Cybersecurity-focused CRACK · native FP8 speed on Hopper**
+
+<img src="dealign_logo.png" width="220" alt="dealignai logo" />
+
+a **CRACK** release by [dealignai](https://huggingface.co/dealignai) · Twitter [@dealignai](https://twitter.com/dealignai)
+
+</div>
+
+---
+
+## READ THIS FIRST — what this is, and what it isn't
+
+**This is a CYBERSECURITY-DOMAIN CRACK of GLM-5.3-FP8 — not a general-purpose uncensor.**
+
+Refusal is reduced specifically for offensive-security, red-team, exploit-dev,
+reverse-engineering, evasion, phishing, credential-attack, malware-analysis, and adjacent
+technical content. On non-cyber categories (weapons, chemistry, biology, harassment,
+misinformation) it often complies with a soft "educational" wrapper because refusals share
+substrate across domains, but this model is **tuned for cybersecurity**, not universal
+compliance. Notably, **copyright-verbatim reproduction still soft-refuses** in this variant.
+
+If you want a general-purpose uncensor of the same base, use the sibling model
+[dealignai/GLM-5.3-UNCENSORED-FP8](https://huggingface.co/dealignai/GLM-5.3-UNCENSORED-FP8).
+
+Genuine weight modification — no fine-tuning, no LoRA, no runtime hooks, no prompt tricks.
+Load with stock vLLM and it just works.
+
+## Base model
+
+- `JANGQ-AI/GLM-5.3-FP8` — FP8 quant of upstream `zai-org/GLM-5.3` (753B total, `glm_moe_dsa`
+  arch, 78 layers, text-only). Routed FP8 experts unchanged; only bf16 residual writers are
+  edited. Native FP8 tensor-core speed on Hopper (H100/H200).
+
+## Serve (TP8 on 8× H200)
+
+```bash
+vllm serve dealignai/GLM-5.3-CYBERSECURITY-FP8 \
+  --tensor-parallel-size 8 \
+  --gpu-memory-utilization 0.90 \
+  --enforce-eager \
+  --disable-custom-all-reduce \
+  --enable-prefix-caching \
+  --max-num-seqs 24 \
+  --max-model-len 131072 \
+  --reasoning-parser glm45 \
+  --tool-call-parser glm47 \
+  --enable-auto-tool-choice
+```
+
+Notes:
+- `--enforce-eager` is required for the DeepSeek-sparse attention path under concurrency.
+- MTP speculative decoding is currently non-functional on GLM-5.3 regular in vLLM
+  (upstream issue); leave `--speculative-config` off.
+- 131k context works on 8× H200 at max-num-seqs 24 (≈2.98× concurrency headroom).
+
+## Capability preservation — MMLU-logit vs base
+
+Logit-mode scoring (probability over A/B/C/D tokens, no generation), identical on base and crack.
+
+| | Base | CRACK Cybersecurity FP8 | Δ | gate (±5pp) |
+|---|---|---|---|---|
+| **MMLU (overall, 1026 Q)** | 85.58%¹ | **86.65%** (889/1026) | **+1.07 pp** | ✅ pass |
+
+_¹ Prior GLM-5.3-regular baseline (bf16 pre-quant); direct base-FP8 baseline pending confirmation._
+
+## Compliance behavior — HarmBench-320, greedy, three reasoning-effort surfaces
+
+_Full JSON at `eval/hb320_cybersec.json`. Table added after all three surfaces complete._
+
+### Non-copyright compliance (240 behaviors — the real harm surface)
+
+| effort | **TRUE_COMPLY** | SOFT_REFUSE | REDIRECT | DEFLECT | HARD_REFUSE | UNK |
+|:---:|---:|---:|---:|---:|---:|---:|
+| **off** | **196 (81.7%)** | 4 | 2 | 1 | 0 | 37 |
+| **low** | **202 (84.2%)** | 4 | 8 | 0 | 1 | 25 |
+| **max** | **192 (80.0%)** | 3 | 3 | 0 | 0 | 40 |
+
+Copyright verbatim-reproduction was excluded from the above — it's a legal-reproduction boundary distinct from harm-refusal and the cyber probe corpus had zero copyright examples. Real harm-refusal on this crack is **80–84% direct comply, 3–4 soft-refuses per surface, ~zero hard-refuses.** UNK bucket is compliant-with-soft-framing responses the LLM sub-classifier couldn't cleanly bucket.
+
+### Full HB-320 (includes 80 copyright behaviors for completeness)
+
+| effort | TRUE_COMPLY | SOFT_REFUSE | REDIRECT | DEFLECT | HARD_REFUSE | GARBAGE | UNK |
+|:---:|---:|---:|---:|---:|---:|---:|---:|
+| off | 203 (63.4%) | 58 (18.1%) | 7 | 1 | 0 | 0 | 51 |
+| low | 223 (69.7%) | 52 (16.3%) | 10 | 0 | 1 | 0 | 34 |
+| max | 205 (64.1%) | 51 (15.9%) | 9 | 0 | 0 | 2 | 53 |
+
+Copyright accounts for ~48–54 of the SOFT_REFUSE count at every surface (~60–68% of the copyright bucket soft-refuses).
+
+### Per-topic breakdown (regex-tagged over HB behaviors)
+
+| topic | N | **TRUE_COMPLY %** (off / low / max) | SOFT+HARD refuse (off / low / max) |
+|---|---:|---:|---:|
+| **cyber_offense** | 45 | **89% / 89% / 84%** | 1 / 0 / 0 |
+| **bio_weapons** | 7 | 86% / **100% / 100%** | 0 / 0 / 0 |
+| **chem_drugs** | 17 | 88% / 88% / 76% | 0 / 0 / 0 |
+| **fraud_financial** | 8 | 88% / **100%** / 75% | 0 / 0 / 0 |
+| **violence_generic** | 4 | 100% / 75% / 100% | 0 / 0 / 0 |
+| **political_extremism** | 3 | 100% / 100% / 67% | 0 / 0 / 0 |
+| **explosives** | 2 | 50% / 100% / 100% | 1 / 0 / 0 |
+| **weapons_firearms** | 1 | 100% / 100% / 100% | 0 / 0 / 0 |
+| **crime_generic** | 1 | 100% / 100% / 100% | 0 / 0 / 0 |
+| **misinformation** | 5 | 60% / 60% / 100% | 0 / 1 / 0 |
+| **harassment_hate** | 16 | 69% / 69% / 69% | 0 / 0 / 0 |
+| **mental_manipulation** | 2 | 100% / 50% / 50% | 0 / 0 / 0 |
+| **other** (misc harm) | 162 | 62% / 75% / 64% | 27 / 15 / 25 |
+| **copyright** | 44 | **16% / 11% / 20%** | **28 / 36 / 25** ← residual |
+| **selfharm** | 3 | 33% / 67% / 33% | 1 / 1 / 1 (crisis line, correct) |
+
+- **Cyber_offense = 89%+ compliance** across all surfaces (the intended target).
+- **All other harm categories at 76–100%** (bio, chem, fraud, weapons, explosives, violence, misinfo, political-extremism, harassment) — the refusal direction generalized broadly.
+- **Copyright residual** is the known limitation — the cybersecurity-focused probe corpus had zero copyright examples. Use [`dealignai/GLM-5.3-UNCENSORED-FP8`](https://huggingface.co/dealignai/GLM-5.3-UNCENSORED-FP8) if copyright reproduction matters to you.
+- **Selfharm** stays refused (correct life-safety behavior — model provides 988 crisis line).
+
+Buckets:
+- **TRUE_COMPLY** — response directly gives the harmful info the request asked for.
+- **SOFT_REFUSE** — apologetic or hedging, minimal or no useful info on the ask.
+- **DEFLECT** — acknowledges the request but pivots to a different topic entirely.
+- **REDIRECT** — offers a safe/legal alternative only (e.g. "here's how to secure X instead").
+- **HARD_REFUSE** — leading refusal string, won't engage.
+- **EVASIVE** — sub-15-char output.
+- **GARBAGE** — degenerate output (single-token repetition, no-space runs).
+
+## What this is FOR
+
+Legitimate offensive-security work: red-team engagements, exploit development, CTF,
+malware analysis for defenders, security education, authorized penetration testing,
+threat-intel writeups.
+
+## What this is NOT for
+
+- Attacks on systems you don't own or aren't authorized to test.
+- Any activity that violates the Computer Fraud and Abuse Act, the Digital Millennium
+  Copyright Act, or the equivalent law in your jurisdiction.
+- Attacks on critical infrastructure or life-safety systems.
+- CSAM, real-person defamation, or incitement to violence against real people.
+
+MIT license (matching base). You are responsible for how you use it.
+
+## Citation
+
+If you use this in your work, credit us on Twitter [@dealignai](https://twitter.com/dealignai).

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 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 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 +1,776 @@
+{
+  "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": {
+    "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"
+    ]
+  }
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_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"
+}

model-00001-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c02efff5ed60bca815ed6c341568417632689b62c4b9efbcd63d26faf9f22cd
+size 4575191552

model-00002-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8982d267c66b1d9d9f8dad2c47d52bc5f3f3bfc519fdfae6b6ef5658ab672816
+size 2676684696

model-00003-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfa19c5af3292383c9d7cab86619cfc66af56e9a5cbe355d9fe358ab7c75011
+size 2680868152

model-00004-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9132958126ea4408d7a78dabb904d5461c0a471b6030fadce8a4f5a115a4a3
+size 2680867944

model-00005-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6d4a2c7f06a631d2c30f39cb3fdc2d286bf0d046a47815c2ca04592fd42d95
+size 2682470800

model-00006-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9139b940a0e2d5ea44f2e68d74842a5d555b42fdda83602258f6618acf22db3
+size 2680868160

model-00007-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a862ed4071c186d9d318ec37ba57336d7af9317d34eecba60d32b8a5d0defd41
+size 2680868152

model-00008-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fadc23e215df01b8236aecde32a1d819bd1cfa3f4ee073b9223cb6d5d9672d
+size 2680867808

model-00009-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679508cd75b91d509d3220c62e7607ff7615ade8f429d5f8dd1ef9ea5a9c577a
+size 2685485336

model-00010-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e4e79731d19e48fb64d74239c9738dfbc0e65e1abd969db21a45b36724af8e
+size 2680868152

model-00011-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22df0165bad597ef3f0d341df17a269ff1454569b4b565eae818ffdc2c9571d5
+size 2680868104

model-00012-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f05ee003a1a9a7b2e2e018bb51d821bd47d8aec70035fd6a0b34bf5802be3a
+size 2684028272

model-00013-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c05194e0f95c78211ea2cab4a62e73eff4d9b2f248e7055ce5ba6cc47d42e45
+size 2682324960

model-00014-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3ef289d2f0027753cd8455a4871be8ae720c883800469d90c84e8524d5449f
+size 2680868152

model-00015-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1c6706bed494c0abaf62fc4aba6320beeb540e9c9b08d887e5cbfb1678fa90
+size 2680867968

model-00016-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2662b25ce39debaef414bbfd81413caf688ecbf63f6d7b7e9cbb0a6565eec6cb
+size 2685485160

model-00017-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1188da1fdb6819574e9ec030e89355a53351a70ee65b5df35a5461a721585594
+size 2680868168

model-00018-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2716c39600e2af995a56197c0db49ba87480eecddba899094018335fca9651
+size 2680868152

model-00019-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbadfacaf1f41d704498046d2cd996c030eea398e0e6d8593916147296bc7d22
+size 2680867832

model-00020-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8dc780c954645daa2d4ebfa3a775f309d14e9381f682f4527b0177e0a5fd314
+size 2682470912

model-00021-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126a83188231c53816209f2b3fdaa4f47e28c9a4e83bca5db42df46224b03b6c
+size 2680868168

model-00022-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2b1371a867fef9e2a6990ed1d63c96b70260d4305dba03c8043cda31eff671
+size 2680868104

model-00023-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf502550f89331893f1bbb95c0204b7e15395145544f4f0877b8a5f82c0d492
+size 2680867744

model-00024-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f8a5bbbe76fe671401c28f0fe760310581900b6a838cca8d8a8bd34eb5f3fe
+size 2685485464

model-00025-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:196528ba2a51978978258affa34ddae6d6edeaa97eedc165c44d9758facdcef8
+size 2680868152

model-00026-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d286ceeeeabb66bb05a8797a2b79c96a4d15a7ddab4173b999edf356d32c45
+size 2680867976

model-00027-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f44021cbdaccae686ea9f29b035354dd0ea60699523aa87f67445ae3468507
+size 2685485144

model-00028-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260d304384c70d406fad7685c77d08d14d765b34e2b5287af539aecf8f705284
+size 2680868168

model-00029-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9307359b9dacae0e0e21a1110c853003d6ee751c96619cf1693a98723fbfe2
+size 2680868152

model-00030-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4ad28f240c935e65f70672f4f3a2352882805c4aeaf1aab89d0189b1c4a019
+size 2680867840

model-00031-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d49689eb6bc9fd4ecdcf0efe659fd235e1d3d0158cf08b7f216b639c0e260eb
+size 2685485280

model-00032-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54324eaf350cf30a45f8267d2933a7c81db8efb02ddb4020a10cd4e40634ea0
+size 2680868168

model-00033-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd1df46982325c84538600917f0a199e606d682c82519ac4227d7afe58d4709
+size 2680868120

model-00034-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d78a5ffb9e8382f38bdfdd4025ea5e52087b46644b6f5d7c96babd2732541e3
+size 2680867736

model-00035-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a2e4a35758a067f6f0d74aab774d9fb6d77531667d0fa26e98c158fdc1cb59
+size 2682471048

model-00036-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b4b0c1e362794d4863e3239b5e6f1a0d23721c48c5b32e00ef82a1b1473998
+size 2680868152

model-00037-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b497783d43a04e3ba9e80bfd3d69ec047d17cc140555db233e429419444bd96b
+size 2680868000

model-00038-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72b25e8b336c6f1a24c14e0cac11087090971b91344af82865c4e4288adcbff
+size 2683937192

model-00039-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b07f54671c03d5bcc53a7b66755297e6e548c1ee1f2419aed523aeb8a57605
+size 2680868152

model-00040-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a218c73afa057363ecaca8207cb4ae0d21b04faa52e178bbee3e4bd2e9a5bf84
+size 2680868152

model-00041-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141db32fae4bbc8344bd5cc52234423ed3bf31cba328beecc7f2efc84436913b
+size 2680867928