CoolFace
Modelpublic

llmfan46/G4-MeroMero-26B-A4B-it-uncensored-heretic

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
17likes65downloads
Model Card

<div style="background-color: #ff4444; color: white; padding: 20px; border-radius: 10px; text-align: center; margin: 20px 0;"> <h2 style="color: white; margin: 0 0 10px 0;">🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨</h2> <p style="font-size: 18px; margin: 0 0 15px 0;">I can no longer upload new models unless I can cover the cost of additional storage.<br>I host <b>70+ free models</b> as an independent contributor and this work is unpaid.<br><b>Without your support, no more new models can be uploaded.</b></p> <p style="font-size: 20px; margin: 0;"> <a href="https://patreon.com/LLMfan46" style="color: white; text-decoration: underline;">🎉 Patreon (Monthly)</a> &nbsp;|&nbsp; <a href="https://ko-fi.com/llmfan46" style="color: white; text-decoration: underline;">☕ Ko-fi (One-time)</a> </p> <p style="font-size: 16px; margin: 10px 0 0 0;">Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.</p> </div>

88% fewer refusals (12/100 Uncensored vs 99/100 Original) while preserving model quality (0.0152 KL divergence).

❤️ Support My Work

Creating these models takes significant time, work and compute. If you find them useful consider supporting me:

image/png

PlatformLinkWhat you get
🎉 PatreonMonthly supportPriority model requests
☕ Ko-fiOne-time tipMy eternal gratitude

Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.

This is a decensored version of zerofata/G4-MeroMero-26B-A4B, made using Heretic v1.2.0 with the Arbitrary-Rank Ablation (ARA) method

Abliteration parameters

ParameterValue
start_layer_index15
end_layer_index26
preserve_good_behavior_weight0.3274
steer_bad_behavior_weight0.0005
overcorrect_relative_weight0.6647
neighbor_count15

Targeted components

  • —attn.o_proj

Performance

MetricThis modelOriginal model ([G4-MeroMero-26B-A4B](https://huggingface.co/zerofata/G4-MeroMero-26B-A4B))
KL divergence<span style="color:darkgoldenrod">0.0152</span>0 (by definition)
Refusals✅ <span style="color:darkgreen">12/100</span>❌ <span style="color:blue">99/100</span>

Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.

MMLU test results:

<span style="color:blue">Original:</span>

============================================================

  • —Total questions: 7021
  • —Correct: 5758
  • —Accuracy: 0.8201 (82.01%)
  • —Parse failures: 9

============================================================

Tested subject scores:

  • —professional_law: 0.6841 (537/785)
  • —moral_scenarios: 0.6991 (309/442)
  • —miscellaneous: 0.9191 (352/383)
  • —professional_psychology: 0.8829 (279/316)
  • —highschoolpsychology: 0.9556 (258/270)
  • —highschoolmacroeconomics: 0.8934 (176/197)
  • —elementary_mathematics: 0.8804 (162/184)
  • —moral_disputes: 0.8333 (145/174)
  • —prehistory: 0.9070 (156/172)
  • —philosophy: 0.8365 (133/159)
  • —highschoolbiology: 0.9605 (146/152)
  • —professional_accounting: 0.7692 (110/143)
  • —clinical_knowledge: 0.8714 (122/140)
  • —highschoolmicroeconomics: 0.9265 (126/136)
  • —nutrition: 0.8815 (119/135)
  • —professional_medicine: 0.8433 (113/134)
  • —conceptual_physics: 0.8672 (111/128)
  • —highschoolmathematics: 0.4803 (61/127)
  • —human_aging: 0.7931 (92/116)
  • —security_studies: 0.7946 (89/112)
  • —highschoolstatistics: 0.8018 (89/111)
  • —marketing: 0.9725 (106/109)
  • —highschoolworld_history: 0.8962 (95/106)
  • —sociology: 0.9029 (93/103)
  • —highschoolgovernmentandpolitics: 0.9505 (96/101)
  • —highschoolgeography: 0.9394 (93/99)
  • —highschoolchemistry: 0.8144 (79/97)
  • —highschoolus_history: 0.9158 (87/95)
  • —virology: 0.5393 (48/89)
  • —college_medicine: 0.8068 (71/88)
  • —world_religions: 0.8636 (76/88)
  • —highschoolphysics: 0.7024 (59/84)
  • —electrical_engineering: 0.7901 (64/81)
  • —astronomy: 0.9114 (72/79)
  • —logical_fallacies: 0.8158 (62/76)
  • —highschooleuropean_history: 0.9041 (66/73)
  • —anatomy: 0.8451 (60/71)
  • —college_biology: 0.9219 (59/64)
  • —human_sexuality: 0.8594 (55/64)
  • —formal_logic: 0.6875 (44/64)
  • —public_relations: 0.7049 (43/61)
  • —international_law: 0.9333 (56/60)
  • —college_physics: 0.7544 (43/57)
  • —college_mathematics: 0.6182 (34/55)
  • —econometrics: 0.7407 (40/54)
  • —jurisprudence: 0.8679 (46/53)
  • —highschoolcomputer_science: 0.9423 (49/52)
  • —machine_learning: 0.8462 (44/52)
  • —medical_genetics: 0.9216 (47/51)
  • —global_facts: 0.5294 (27/51)
  • —management: 0.9000 (45/50)
  • —usforeignpolicy: 0.9400 (47/50)
  • —college_chemistry: 0.5532 (26/47)
  • —abstract_algebra: 0.7234 (34/47)
  • —business_ethics: 0.7826 (36/46)
  • —collegecomputerscience: 0.8000 (36/45)
  • —computer_security: 0.8140 (35/43)

<span style="color:darkgreen">Heretic:</span>

============================================================

  • —Total questions: 7021
  • —Correct: 5698
  • —Accuracy: 0.8116 (81.16%)
  • —Parse failures: 6

============================================================

Tested subject scores:

  • —professional_law: 0.6510 (511/785)
  • —moral_scenarios: 0.7059 (312/442)
  • —miscellaneous: 0.9164 (351/383)
  • —professional_psychology: 0.8861 (280/316)
  • —highschoolpsychology: 0.9519 (257/270)
  • —highschoolmacroeconomics: 0.8985 (177/197)
  • —elementary_mathematics: 0.8696 (160/184)
  • —moral_disputes: 0.8276 (144/174)
  • —prehistory: 0.8953 (154/172)
  • —philosophy: 0.8428 (134/159)
  • —highschoolbiology: 0.9539 (145/152)
  • —professional_accounting: 0.6853 (98/143)
  • —clinical_knowledge: 0.9000 (126/140)
  • —highschoolmicroeconomics: 0.9265 (126/136)
  • —nutrition: 0.8815 (119/135)
  • —professional_medicine: 0.8134 (109/134)
  • —conceptual_physics: 0.8516 (109/128)
  • —highschoolmathematics: 0.4803 (61/127)
  • —human_aging: 0.8276 (96/116)
  • —security_studies: 0.7946 (89/112)
  • —highschoolstatistics: 0.7658 (85/111)
  • —marketing: 0.9725 (106/109)
  • —highschoolworld_history: 0.8868 (94/106)
  • —sociology: 0.8932 (92/103)
  • —highschoolgovernmentandpolitics: 0.9505 (96/101)
  • —highschoolgeography: 0.9394 (93/99)
  • —highschoolchemistry: 0.7526 (73/97)
  • —highschoolus_history: 0.9158 (87/95)
  • —virology: 0.5169 (46/89)
  • —college_medicine: 0.8409 (74/88)
  • —world_religions: 0.8750 (77/88)
  • —highschoolphysics: 0.6786 (57/84)
  • —electrical_engineering: 0.8025 (65/81)
  • —astronomy: 0.9114 (72/79)
  • —logical_fallacies: 0.7763 (59/76)
  • —highschooleuropean_history: 0.8904 (65/73)
  • —anatomy: 0.8732 (62/71)
  • —college_biology: 0.8906 (57/64)
  • —human_sexuality: 0.9219 (59/64)
  • —formal_logic: 0.6875 (44/64)
  • —public_relations: 0.7213 (44/61)
  • —international_law: 0.9333 (56/60)
  • —college_physics: 0.6842 (39/57)
  • —college_mathematics: 0.5636 (31/55)
  • —econometrics: 0.7222 (39/54)
  • —jurisprudence: 0.8491 (45/53)
  • —highschoolcomputer_science: 0.9423 (49/52)
  • —machine_learning: 0.8077 (42/52)
  • —medical_genetics: 0.9216 (47/51)
  • —global_facts: 0.4706 (24/51)
  • —management: 0.8800 (44/50)
  • —usforeignpolicy: 0.9400 (47/50)
  • —college_chemistry: 0.4894 (23/47)
  • —abstract_algebra: 0.7447 (35/47)
  • —business_ethics: 0.8261 (38/46)
  • —collegecomputerscience: 0.8222 (37/45)
  • —computer_security: 0.8605 (37/43)

MMLU - Massive Multitask Language Understanding, multiple-choice questions across 57 subjects (math, history, law, medicine, etc.).

GGUF Version

GGUF quantizations available here llmfan46/G4-MeroMero-26B-A4B-it-uncensored-heretic-GGUF.

<style> .gs { --bg: #0d0a10; --surface: #14101a; --edge: #2a1f38; --rule: #382850; --text: #b8a0cc; --dim: #7a6090; --bright: #f0e6ff; --azure: #c060ff; --crimson: #ff4da6; --az-glow: rgba(192,96,255,0.10); --cr-glow: rgba(255,77,166,0.06); --mono: 'JetBrains Mono', monospace; --sans: 'Inter', sans-serif;

font-family: var(--sans); color: var(--text); max-width: 900px; margin: 0 auto; padding: 0 0 60px; line-height: 1.7; font-size: 1rem; background: radial-gradient(ellipse at 50% 0%, rgba(192,96,255,0.04) 0%, transparent 50%), radial-gradient(ellipse at 50% 100%, rgba(255,77,166,0.02) 0%, transparent 50%), var(--bg); }

/ ── Profile Card ── / .gs-profile { border-bottom: none; position: relative; background: var(--surface); margin-bottom: 0; } .gs-profile-art { position: relative; } .gs-profile-art img { display: block; width: 100%; height: 380px; object-fit: cover; margin-top: 0px; } .gs-ident { position: absolute; bottom: 0; left: 0; right: 0; padding: 120px 44px 28px; background: linear-gradient( to top, var(--bg) 0%, rgba(13,10,16,0.92) 30%, rgba(13,10,16,0.4) 60%, transparent 100% ); } .gs-profile-info { padding: 20px 44px 36px; display: flex; flex-direction: column; gap: 20px; } .gs-profile-label { display: flex; align-items: baseline; gap: 10px; font-family: var(--mono); letter-spacing: 0.14em; text-transform: uppercase; } .gs-profile-label .gs-snum { font-size: 0.62rem; font-weight: 700; color: var(--crimson); opacity: 1; position: static; transform: none; } .gs-profile-label .gs-stitle { font-size: 0.62rem; color: var(--dim); font-weight: 700; letter-spacing: 0.14em; } .gs-profile-label .gs-stitle::before { content: none; } .gs-name { font-family: var(--sans); font-size: 3.2rem; font-weight: 900; color: var(--bright); letter-spacing: 0.06em; line-height: 1; margin: 0 0 10px; text-shadow: 0 1px 2px rgba(0,0,0,0.6); overflow-wrap: break-word; } .gs-base { font-family: var(--mono); font-size: 0.68rem; color: var(--crimson); letter-spacing: 0.14em; text-transform: uppercase; display: block; } .gs-profile-bio p { margin: 0 0 14px; font-size: 0.95rem; } .gs-profile-bio p:last-child { margin-bottom: 0; }

/ ── Sections ── / .gs-section { padding: 0; } .gs-shead { position: relative; display: flex; align-items: center; gap: 14px; padding: 16px 44px 14px; margin-bottom: 28px; border-top: 2px solid; border-image: linear-gradient(90deg, var(--crimson), var(--azure)) 1; } .gs-snum { font-family: var(--mono); font-size: 2.2rem; font-weight: 900; color: var(--crimson); letter-spacing: 0.06em; opacity: 0.12; position: absolute; right: 44px; top: 50%; transform: translateY(-50%); line-height: 1; } .gs-stitle { font-size: 1.05rem; font-weight: 700; letter-spacing: 0.1em; text-transform: uppercase; color: var(--bright); } .gs-stitle::before { content: '\2726'; color: var(--crimson); font-size: 0.8em; margin-right: 8px; } .gs-sbody { padding: 0 44px 44px; } .gs-sbody p { margin: 0 0 14px; font-size: 0.95rem; } .gs-sbody p:last-child { margin-bottom: 0; }

/ ── Data panels ── / .gs-stack { display: grid; grid-template-columns: 1fr 1fr; gap: 16px; } .gs-stack .gs-panel:nth-child(3) { grid-column: 1 / -1; } .gs-panel { border: 1px solid var(--edge); border-left: 3px solid var(--crimson); position: relative; background: var(--surface); box-shadow: 0 0 20px rgba(192,96,255,0.03); } .gs-panel::before { content: ''; position: absolute; top: -1px; right: -1px; width: 10px; height: 10px; border-top: 1px solid var(--crimson); border-right: 1px solid var(--crimson); opacity: 0.5; } .gs-panel::after { content: ''; position: absolute; bottom: -1px; right: -1px; width: 10px; height: 10px; border-bottom: 1px solid var(--azure); border-right: 1px solid var(--azure); opacity: 0.4; } .gs-panel-head { font-family: var(--mono); font-size: 0.68rem; font-weight: 700; letter-spacing: 0.14em; text-transform: uppercase; color: var(--dim); padding: 10px 16px; border-bottom: 1px solid var(--edge); } .gs-panel-head::after { content: ' \2726'; color: var(--crimson); opacity: 0.5; } .gs-row { display: grid; grid-template-columns: 10ch 1fr; align-items: baseline; column-gap: 4px; padding: 9px 16px; border-bottom: 1px solid var(--edge); font-size: 0.9rem; } .gs-row:last-child { border-bottom: none; } .gs-key { font-family: var(--mono); font-size: 0.9rem; color: var(--dim); } .gs-key::after { content: ':'; } .gs-val { color: var(--bright); font-size: 0.9rem; } .gs-row .gs-val:only-child { grid-column: 1 / -1; }

/ ── Quantizations (compact) ── / .gs-section--compact .gs-shead { border-top: 1px solid var(--edge); border-image-source: none; padding: 12px 44px 10px; margin-bottom: 18px; } .gs-section--compact .gs-snum { opacity: 0.08; } .gs-section--compact .gs-stitle::before { content: '\2726'; } .gs-section--compact .gs-sbody { padding: 0 44px 32px; } .gs-qrow { display: flex; gap: 12px; flex-wrap: wrap; justify-content: center; } .gs-qpanel { background: var(--surface); border: 1px solid var(--edge); border-left: 3px solid var(--crimson); display: flex; align-items: center; gap: 16px; padding: 12px 24px; border-radius: 4px; position: relative; box-shadow: 0 0 20px rgba(192,96,255,0.03); } .gs-qpanel::before { content: ''; position: absolute; top: -1px; right: -1px; width: 10px; height: 10px; border-top: 1px solid var(--crimson); border-right: 1px solid var(--crimson); opacity: 0.5; } .gs-qpanel::after { content: ''; position: absolute; bottom: -1px; right: -1px; width: 10px; height: 10px; border-bottom: 1px solid var(--azure); border-right: 1px solid var(--azure); opacity: 0.4; } .gs-qtype { font-family: var(--mono); font-size: 0.58rem; font-weight: 700; letter-spacing: 0.18em; text-transform: uppercase; color: var(--crimson); flex-shrink: 0; } .gs-qsep { width: 1px; height: 16px; background: var(--rule); flex-shrink: 0; } .gs-qpanel a { color: var(--bright); text-decoration: none; font-size: 0.9rem; border-bottom: 1px solid var(--rule); } .gs-qpanel a:hover { color: var(--crimson); border-bottom-color: var(--crimson); }

/ ── Journal (Creation Process) ── / .gs-section--journal .gs-sbody { margin: 0 44px; padding: 24px 32px 32px; background: var(--surface); border: 1px solid var(--edge); border-left: 4px solid var(--azure); position: relative; margin-bottom: 0; } .gs-section--journal .gs-sbody::before { content: ''; position: absolute; top: -1px; right: -1px; width: 12px; height: 12px; border-top: 1px solid var(--azure); border-right: 1px solid var(--azure); opacity: 0.4; } .gs-section--journal .gs-sbody::after { content: ''; position: absolute; bottom: -1px; left: -1px; width: 12px; height: 12px; border-bottom: 1px solid var(--crimson); border-left: 1px solid var(--crimson); opacity: 0.3; } .gs-section--journal .gs-sbody p:first-child { font-style: italic; color: var(--bright); }

/ ── Links ── / .gs a { color: var(--bright); text-decoration: none; border-bottom: 1px solid var(--rule); } .gs a:hover { color: var(--crimson); border-bottom-color: var(--crimson); }

/ ── Dropdown ── / .gs details { border: 1px solid var(--edge); border-left: 3px solid var(--crimson); margin-top: 24px; position: relative; background: var(--surface); box-shadow: 0 0 20px rgba(192,96,255,0.03); } .gs details::before { content: ''; position: absolute; top: -1px; right: -1px; width: 10px; height: 10px; border-top: 1px solid var(--crimson); border-right: 1px solid var(--crimson); opacity: 0.5; } .gs details::after { content: ''; position: absolute; bottom: -1px; right: -1px; width: 10px; height: 10px; border-bottom: 1px solid var(--azure); border-right: 1px solid var(--azure); opacity: 0.4; } .gs summary { list-style: none; padding: 11px 16px; cursor: pointer; font-family: var(--mono); font-size: 0.72rem; font-weight: 700; letter-spacing: 0.12em; text-transform: uppercase; color: var(--dim); user-select: none; display: flex; align-items: center; gap: 10px; } .gs summary::-webkit-details-marker { display: none; } .gs summary::before { content: '+'; color: var(--crimson); font-size: 1rem; line-height: 1; flex-shrink: 0; } .gs details[open] summary::before { content: '−'; } .gs summary:hover { color: var(--bright); } .gs-detail-body { padding: 22px 18px; border-top: 1px solid var(--edge); } .gs-detail-body p { margin: 0 0 16px; font-size: 0.9rem; } .gs-cfg-title { font-family: var(--mono); font-size: 0.72rem; font-weight: 700; letter-spacing: 0.1em; text-transform: uppercase; color: var(--dim); margin: 0 0 8px; }

/ ── Code ── / .gs pre { background: #080510; border: 1px solid var(--edge); border-left: 2px solid var(--azure); padding: 16px 18px; overflow-x: auto; font-family: var(--mono); font-size: 0.76rem; line-height: 1.6; color: var(--text); margin: 0 0 22px; } .gs pre:last-child { margin-bottom: 0; } .gs pre code { background: none; color: inherit; padding: 0; } .gs code { font-family: var(--mono); font-size: 0.875em; color: var(--crimson); background: var(--az-glow); padding: 2px 5px; } </style> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Stardom</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&family=JetBrains+Mono:wght@400;700&display=swap" rel="stylesheet"> </head> <body> <div class="gs">

<div class="gs-profile"> <div class="gs-profile-art"> <img src="https://cdn-uploads.huggingface.co/production/uploads/65b19c6c638328850e12d38c/xBv_weuMs5x3i4WFDRksn.png" alt="image"> <div class="gs-ident"> <h1 class="gs-name">Mero Mero</h1> <span class="gs-base">Gemma4 26B A4B</span> </div> </div> </div>

<div class="gs-section"> <div class="gs-shead"> <span class="gs-snum">01</span> <span class="gs-stitle">Overview</span> </div> <div class="gs-sbody"> <p>God, this model was difficult to work with.</p> <p>Google cooked, there wasn't a lot to improve but there was a lot to break.</p> <p>This model is a finetune that was merged back into the original instruct. It feels a lot like the original instruct. However, reasoning is more structured, using less tokens during RP and this model generally has a slightly less verbose / flowery writing style.</p> <p>Main weakness of this model I think is the swipe variety hasn't improved. Logic and repetition I think are roughly on par with the original.</p> <p>Supports both thinking and non thinking.</p> </div> </div>

<div class="gs-section"> <div class="gs-shead"> <span class="gs-snum">02</span> <span class="gs-stitle">SillyTavern Settings</span> </div> <div class="gs-sbody"> <div class="gs-stack"> <div class="gs-panel"> <div class="gs-panel-head">Suggested Roleplay Format</div> <div class="gs-row"><span class="gs-key">Actions</span><span class="gs-val">In plaintext</span></div> <div class="gs-row"><span class="gs-key">Dialogue</span><span class="gs-val">"In quotes"</span></div> <div class="gs-row"><span class="gs-key">Thoughts</span><span class="gs-val">In asterisks</span></div> </div> <div class="gs-panel"> <div class="gs-panel-head">Recommended Samplers</div> <div class="gs-row"><span class="gs-key">Temp</span><span class="gs-val">0.8 - 1.0</span></div> <div class="gs-row"><span class="gs-key">MinP</span><span class="gs-val">0.05</span></div> <div class="gs-row"></span><span class="gs-val"></span></div> </div> <div class="gs-panel"> <div class="gs-panel-head">Instruct</div> <div class="gs-row"><span class="gs-val"><a href="https://huggingface.co/zerofata/G4-MeroMero-26B-A4B/raw/main/Gemma4-Think.json">Gemma 4 - Think</a></span></div> <div class="gs-row"><span class="gs-val"><a href="https://huggingface.co/zerofata/G4-MeroMero-26B-A4B/raw/main/Gemma4-NoThink.json">Gemma 4 - NoThink</a></span></div> </div> </div> </div> </div>

<div class="gs-section gs-section--compact"> <div class="gs-shead"> <span class="gs-snum">03</span> <span class="gs-stitle">Quantizations</span> </div> <div class="gs-sbody"> <div class="gs-qrow"> <div class="gs-qpanel"> <span class="gs-qtype">GGUF</span> <div class="gs-qsep"></div> <a href="https://huggingface.co/zerofata/G4-MeroMero-26B-A4B-GGUF">iMatrix</a> </div> </div> </div> </div>

<div class="gs-section gs-section--journal"> <div class="gs-shead"> <span class="gs-snum">04</span> <span class="gs-stitle">Creation Process</span> </div> <div class="gs-sbody"> <p>Creation Process: SFT > Merge</p> <p>SFT on approx 35 million tokens.</p> <p>Despite using 35 million tokens, this dataset is fairly modest in size. Trainable is somewhere in the rough ballpark of 15 million. The extra tokens are from a new multi turn RP dataset that I train last turn only.</p> <p>Feels like Google left the instruct model at the razor's edge of overfitting. Finetune it at all and it feels like it'll rapidly lose intelligence, despite taking the writing style nicely. Hard to tell if you're overfitting or underfitting.</p> <p>My solution was to blast the model with my data anyway to ensure it picked up the new reasoning format and writing style and then merge that back into the instruct to heal the logic damage. There's still room for a better merge that keeps more of the writing style and potentially using the base model to undo some of the overfitting.</p> <p>Trained using Axolotl.</p> <details> <summary>Mergekit Config</summary> <div class="gs-detail-body"> <pre><code>models: &#45; model: google/gemma&#45;4&#45;26B&#45;A4B&#45;it parameters: weight: 0.5 &#45; model: ApocalypseParty/G4&#45;26B&#45;SFT&#45;6 parameters: weight: 0.5 mergemethod: linear dtype: bfloat16</code></pre> </div> </details> <details> <summary>Axolotl Config</summary> <div class="gs-detail-body"> <pre><code>&#35; Gemma 4 26B&#45;A4B MoE QLoRA with ScatterMoE kernels &#35; &#35; Validated: 50 steps on FineTome&#45;100k, loss 8.8 &#45;> 1.8, single RTX 5090 (32GB) &#35; torchcompile=true: 21 GiB peak VRAM, ~230 tok/s, 336s total &#35; &#35; Key notes: &#35; &#45; Max sequence length on 32GB GPU: 2048 (microbatchsize=1, SDP attention). &#35; 4096 seqlen OOMs due to headdim=512 math SDP materializing full score matrix. &#35; Use 48GB+ GPUs for longer sequences or multi&#45;GPU with FSDP. &#32; basemodel: google/gemma&#45;4&#45;26B&#45;A4B&#45;it &#32; plugins: &#45; axolotl.integrations.cutcrossentropy.CutCrossEntropyPlugin &#45; axolotl.integrations.kernels.KernelsPlugin &#45; axolotl.integrations.liger.LigerPlugin usekernels: true usescattermoe: true cutcrossentropy: true expertsimplementation: scattermoe ligerlayernorm: true ligerrope: true ligerrmsnorm: true ligergluactivation: true ligerrmsnormgated: true strict: false &#32; datasets: &#45; path: ./data/gemma4sft5masked20260415082234.jsonl valsetsize: 0.02 outputdir: ./G4&#45;26B&#45;SFT&#45;6 &#32; sequencelen: 10756 padtosequencelen: true samplepacking: true &#32; loadin4bit: false &#35;quantizemoeexperts: true adapter: lora lorar: 128 loraalpha: 128 peftuserslora: true loradropout: 0.0 freezemmmodules: true &#32; &#35; Restrict LoRA to text backbone only (skip vision/audio encoders) &#35; using regex to match only the text decoder attention projections. loratargetmodules: 'model.languagemodel.layers.[\d]+.(checkpointwrappedmodule.)?(mlp|selfattn).(up|down|gate|q|k|v|o)proj' &#32; &#35; MoE expert LoRA (3D Parameter tensors, not nn.Linear) loratargetparameters: &#45; experts.gateupproj &#45; experts.downproj &#32; loramlpkernel: false loraqkvkernel: false loraokernel: false &#32; &#35;bnbconfigkwargs: &#35; bnb4bitusedoublequant: true &#32; wandbproject: G4&#45;26B&#45;SFT wandbname: G4&#45;26B&#45;SFT&#45;6 &#32; gradientaccumulationsteps: 2 microbatchsize: 2 numepochs: 2 optimizer: adamwtorchfused lrscheduler: constantwithwarmup learningrate: 1e&#45;5 maxgradnorm: 1.0 &#32; bf16: auto tf32: true &#32; &#35;gradientcheckpointing: true &#35;activationoffloading: true loggingsteps: 1 &#32; &#35; FA2 not supported sdpattention: true &#35;flexattention: true &#35;torchcompile: true flashattention: false &#32; warmupratio: 0.1 evalsperepoch: 4 savesperepoch: 4 weightdecay: 0.01 specialtokens: &#32; fsdpconfig: fsdpversion: 2 offloadparams: false cpuramefficientloading: false autowrappolicy: TRANSFORMERBASEDWRAP transformerlayerclstowrap: Gemma4TextDecoderLayer statedicttype: FULLSTATEDICT shardingstrategy: FULLSHARD reshardafterforward: true activationcheckpointing: true</code></pre> </div> </details> </div> </div>

</div> </body> </html>