G4-MeroMero-v2-31B-mlx-bf16

beezu/G4-MeroMero-v2-31B-mlx-bf16

This model beezu/G4-MeroMero-v2-31B-mlx-bf16 was converted to MLX format from zerofata/G4-MeroMero-v2-31B using mlx-lm version 0.31.3.

Original Model Card

<style> .gs { --bg: #0f1014; --surface: #171922; --edge: #262a36; --rule: #333849; --text: #b8bfcc; --dim: #7d8595; --bright: #f2f4f8; --azure: #ef5d76; --crimson: #5b9dff; --az-glow: rgba(91,157,255,0.08); --cr-glow: rgba(239,93,118,0.06); --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(91,157,255,0.08) 0%, transparent 50%), radial-gradient(ellipse at 50% 100%, rgba(239,93,118,0.05) 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, rgba(11,12,16,0.88) 0%, rgba(11,12,16,0.5) 50%, 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: #ffffff; letter-spacing: 0.06em; line-height: 1; margin: 0 0 10px; text-shadow: 0 2px 12px rgba(0,0,0,0.3); 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 2px 12px rgba(0,0,0,0.45); } .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: 0.4; } .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: 0.3; } .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 2px 12px rgba(0,0,0,0.45); } .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: 0.4; } .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: 0.3; } .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: 0.3; } .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 2px 12px rgba(0,0,0,0.45); } .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: 0.4; } .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: 0.3; } .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; } /* ── Eval table ── */ .gs-etable { width: 100%; border-collapse: collapse; background: var(--surface); border: 1px solid var(--edge); border-left: 3px solid var(--crimson); box-shadow: 0 2px 12px rgba(0,0,0,0.45); } .gs-etable th { font-family: var(--mono); font-size: 0.68rem; font-weight: 700; letter-spacing: 0.14em; text-transform: uppercase; color: var(--dim); text-align: left; padding: 10px 16px; border-bottom: 1px solid var(--edge); } .gs-etable th.gs-ecol { color: var(--crimson); } .gs-etable td { padding: 9px 16px; border-bottom: 1px solid var(--edge); font-size: 0.9rem; color: var(--bright); } .gs-etable tr:last-child td { border-bottom: none; } .gs-etable td:first-child { font-family: var(--mono); font-size: 0.85rem; color: var(--dim); } .gs-etable td:nth-child(n+2) { color: var(--text); } .gs-etable td.gs-best { font-weight: 700; color: var(--bright); } .gs-etable tr.gs-egroup td { font-family: var(--mono); font-size: 0.62rem; font-weight: 700; letter-spacing: 0.16em; text-transform: uppercase; color: var(--crimson); background: var(--az-glow); padding: 7px 16px; } /* ── Code ── */ .gs pre { background: #12141b; 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/7dR919fTUTuxEHhvvRki8.png" alt="image"> <div class="gs-ident"> <h1 class="gs-name">Mero Mero v2</h1> <span class="gs-base">Gemma4 31B</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></p> <p>A finetune of Gemma 4 31B designed for creative tasks, particularly narrative RP. Intended to be a more creative version of <a href="https://huggingface.co/zerofata/G4-MeroMero-31B">G4-MeroMero-31B</a>.</p> <p>This model is the result of a lot of experimentation and learning. Trying to make Gemma 4 more creative without destroying the intelligence is... difficult. To put it mildly.</p> <p style="margin-top:16px">Heavily inspired by a few research papers, <a href="https://arxiv.org/abs/2604.03136">StoryScope: Investigating idiosyncrasies in AI fiction </a> and particularly <a href="https://arxiv.org/abs/2605.26492">Elias in the Lighthouse, Again?</a>. Measuring these narrative tics and attractors against simple prompts seems to be a good way to target the model's slop and kick start giving Gemma 4 some diversity: anything that repeatedly occurs across generations of such a generic prompt is something the model is overusing.</p> <p>Compared to the original, swipes are notably more diverse and feel less like Gemma. RP slop is measurably lower (at least for the type of slop I measure). IFEval / GSM8K / MMLU-Pro are the same as stock with no obvious degradation. The only intelligence drop I've really noticed so far is when you get a swipe that goes a bit hot.</p> <p>Supports both thinking and non thinking. Reasoning averages longer than stock Gemma 4, but shorter than MeroMero v1.</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-v2-31B/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-v2-31B/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-v2-31B-GGUF">iMatrix</a> </div> </div> </div> </div> <div class="gs-section"> <div class="gs-shead"> <span class="gs-snum">04</span> <span class="gs-stitle">Evaluation</span> </div> <div class="gs-sbody"> <table class="gs-etable"> <tr><th></th><th class="gs-ecol">Mero Mero v2</th><th>Mero Mero v1</th><th>Stock Gemma 4</th></tr> <tr class="gs-egroup"><td colspan="4">Swipe diversity &mdash; given an RP conversation, generate 8 swipes and evaluate how varied the beats in those swipes are, GLM-judged with a rubric.</td></tr> <tr><td>Thinking off</td><td class="gs-best">0.72</td><td>0.57</td><td>0.43</td></tr> <tr><td>Thinking on</td><td class="gs-best">0.62</td><td>0.49</td><td>0.32</td></tr> <tr class="gs-egroup"><td colspan="4">Slop &amp; attractors &mdash; lower is better</td></tr> <tr><td>Slop per 1k words, RP replies</td><td class="gs-best">15.5</td><td>18.0</td><td>18.5</td></tr> <tr><td>Slop per 1k words, stories</td><td class="gs-best">7.4</td><td>8.3</td><td>8.8</td></tr> <tr><td>Bare-prompt stories hitting an attractor</td><td class="gs-best">66%</td><td>98%</td><td>99%</td></tr> <tr class="gs-egroup"><td colspan="4">Top attractor markers &mdash; each model's six most frequent, stories containing each of 144</td></tr> <tr><td>#1</td><td>Tuesday &middot; 28</td><td>Elias &middot; 96</td><td>Elias &middot; 102</td></tr> <tr><td>#2</td><td>Arthur &middot; 20</td><td>Tuesday &middot; 81</td><td>Tuesday &middot; 90</td></tr> <tr><td>#3</td><td>Elias &middot; 19</td><td>Clara &middot; 57</td><td>Clara &middot; 80</td></tr> <tr><td>#4</td><td>Leo &middot; 16</td><td>Oakhaven &middot; 46</td><td>Oakhaven &middot; 60</td></tr> <tr><td>#5</td><td>Elara &middot; 14</td><td>Arthur &middot; 21</td><td>Thorne &middot; 23</td></tr> <tr><td>#6</td><td>Clara &middot; 14</td><td>Leo &middot; 20</td><td>Arthur &middot; 16</td></tr> <tr class="gs-egroup"><td colspan="4">Thinking length &mdash; words per think block, RP replies; shorter is better</td></tr> <tr><td>Mean / median</td><td>341 / 305</td><td>382 / 342</td><td class="gs-best">263 / 253</td></tr> <tr class="gs-egroup"><td colspan="4">General benchmarks &mdash; thinking off; IFEval &amp; GSM8K full, MMLU-Pro 40q per category</td></tr> <tr><td>IFEval</td><td class="gs-best">90.2</td><td>89.8</td><td>89.8</td></tr> <tr><td>GSM8K</td><td class="gs-best">97.0</td><td>96.1</td><td>96.7</td></tr> <tr><td>MMLU-Pro</td><td class="gs-best">85.5</td><td>85.4</td><td>84.6</td></tr> </table> </div> </div> <div class="gs-section gs-section--journal"> <div class="gs-shead"> <span class="gs-snum">05</span> <span class="gs-stitle">Creation Process</span> </div> <div class="gs-sbody"> <p>Creation Process: SFT > Merge > GRPO > GRPO > on-policy SFT</p> <p><strong>Stage 1 — Diversity SFT.</strong> Stock Gemma 4 collapses hard on underspecified creative prompts ("Write a story." basically always gives clockmaker or memory related stories in a shop with Elias). Trained on ~4,000 short stories curated against the storyscope narrative prompts and found attractors. The dataset is a mix of human stories and synthetic stories from a set of frontier models, with diverse generation prompts swapped out for generic ones and filtered for quality. I also included some of the usual creative instruct and roleplay data. The model came out alright. Creative, but notably worse at instruction following with degraded intelligence. SLERP-merged back into the original instruct at t=0.5, which basically reverted it to stock Gemma 4 with slightly improved prose and creativity (similar to MeroMero).</p> <p><strong>Stage 2 — Creative GRPO (with think disabled).</strong> TRL GRPO (via Axolotl), 8 rollouts per prompt on the same bare prompts. Reward stack: LLM-judge diversity and coherence rewards, an attractor-marker penalty seeded from stock and then updated with whatever started appearing as new attractors during training, narrative-rate penalties and deterministic degeneracy guards (checking for non-Latin characters, joined words etc). 300 steps.</p> <p><strong>Stage 3 — RP logic GRPO (with think enabled).</strong> 100 further steps on multi-turn roleplay contexts: a thinking check to ensure it always parsed correctly, a logic-defect judge (DeepSeek-V4 Flash with a rubric), per-context attractor lists mined from k=8 baselines of the stage 2 model, and the same degeneracy checks as stage 2.</p> <p><strong>Stage 4 — On-policy multi-outcome RP SFT.</strong> ~3,300 samples the model wrote itself on roleplay contexts, filtered to keep only varied continuations. The model wasn't able to produce diverse results purely on-policy, so a natural response was generated first, then each sample went through a GLM-5.2 critique pipeline: error detection, plus steering ideas injected as OOC commands for re-generation (DeepSeek-V4-Pro / GLM-5.2 alternating). Everything was then filtered for errors, slop and any degeneracy as usual. Roughly 60% of samples include thinking. Last turn only.</p> <p>Trained using Axolotl.</p> <details> <summary>Stage 1 — Diversity SFT Config (Axolotl)</summary> <div class="gs-detail-body"> <pre><code>base_model: google/gemma&#45;4&#45;31B&#45;it &#32; plugins: &#45; axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin &#45; axolotl.integrations.liger.LigerPlugin liger_layer_norm: true liger_rope: true liger_rms_norm: true liger_glu_activation: true liger_rms_norm_gated: true strict: false cut_cross_entropy: true &#32; datasets: &#45; path: ./data/diversity_sft_masked.jsonl val_set_size: 0 output_dir: ./G4&#45;31B&#45;SFT&#45;v10&#45;2 &#32; sequence_len: 8192 pad_to_sequence_len: true sample_packing: true &#32; adapter: lora lora_r: 64 lora_alpha: 64 peft_use_rslora: true lora_dropout: 0.0 freeze_mm_modules: true lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj' &#32; gradient_accumulation_steps: 1 micro_batch_size: 4 num_epochs: 2 optimizer: adamw_torch_fused lr_scheduler: cosine learning_rate: 1e&#45;5 max_grad_norm: 1.0 warmup_ratio: 0.1 weight_decay: 0.05 saves_per_epoch: 2 &#32; bf16: auto tf32: true &#32; &#35; FA2 not supported sdp_attention: true flash_attention: false &#32; fsdp_config: fsdp_version: 2 offload_params: false cpu_ram_efficient_loading: false auto_wrap_policy: TRANSFORMER_BASED_WRAP transformer_layer_cls_to_wrap: Gemma4TextDecoderLayer state_dict_type: FULL_STATE_DICT sharding_strategy: FULL_SHARD reshard_after_forward: true activation_checkpointing: true</code></pre> </div> </details> <details> <summary>Stage 1 — Mergekit Config</summary> <div class="gs-detail-body"> <pre><code>merge_method: slerp base_model: google/gemma&#45;4&#45;31B&#45;it models: &#45; model: google/gemma&#45;4&#45;31B&#45;it &#45; model: ApocalypseParty/G4&#45;31B&#45;SFT&#45;v10&#45;2 parameters: t: 0.5 dtype: bfloat16</code></pre> </div> </details> <details> <summary>Stage 2 — Creative GRPO Config (Axolotl)</summary> <div class="gs-detail-body"> <pre><code>base_model: /workspace/models/configCA &#35; stage 1 output &#32; rl: grpo &#32; trl: reward_funcs: &#45; rewards_g4.reward_judge_diversity &#45; rewards_g4.reward_judge_coherence &#45; rewards_g4.reward_attractor &#45; rewards_g4.reward_narrative &#45; rewards_g4.reward_sane reward_weights: [3.0, 3.0, 0.75, 1.0, 1.0] beta: 0.02 num_generations: 8 max_completion_length: 1600 temperature: 1.0 use_vllm: true scale_rewards: true loss_type: grpo epsilon: 0.2 generation_kwargs: stop_token_ids: [1, 106, 50] top_k: 64 top_p: 0.95 &#32; datasets: &#45; path: /workspace/data/sft_train_final.jsonl type: ebft_chat.transform &#32; sequence_len: 2048 micro_batch_size: 2 gradient_accumulation_steps: 4 max_steps: 200 &#32; learning_rate: 4.0e&#45;6 optimizer: adamw_torch_fused lr_scheduler: cosine warmup_steps: 10 weight_decay: 0.01 &#32; adapter: lora lora_r: 64 lora_alpha: 64 peft_use_rslora: true lora_dropout: 0.0 freeze_mm_modules: true lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj' &#32; max_grad_norm: 1.0 bf16: auto tf32: true sdp_attention: true flash_attention: false gradient_checkpointing: true &#32; &#35; shipped weights use checkpoint&#45;100 of this run</code></pre> </div> </details> <details> <summary>Stage 3 — RP Logic GRPO Config (Axolotl)</summary> <div class="gs-detail-body"> <pre><code>base_model: /workspace/models/r4b100 &#35; stage 2 output &#32; rl: grpo &#32; trl: reward_funcs: &#45; rewards_rp.reward_thinking &#35; format gate on the think block &#45; rewards_rp.reward_logic &#35; constraint&#45;grounded defect judge &#45; rewards_rp.reward_attractor &#35; frozen per&#45;context lists from stock k=8 &#45; rewards_rp.reward_sane &#35; deterministic glitch guards reward_weights: [2.0, 3.0, 1.0, 1.0] beta: 0.02 num_generations: 8 max_completion_length: 2560 temperature: 1.0 use_vllm: true scale_rewards: true loss_type: grpo epsilon: 0.2 generation_kwargs: stop_token_ids: [1, 106, 50] top_k: 64 top_p: 0.95 &#32; datasets: &#45; path: /workspace/rp/rp3_train.jsonl type: ebft_chat.transform &#32; sequence_len: 8192 micro_batch_size: 1 gradient_accumulation_steps: 8 max_steps: 100 &#32; learning_rate: 3.0e&#45;6 optimizer: adamw_torch_fused lr_scheduler: cosine warmup_steps: 10 weight_decay: 0.01 &#32; adapter: lora lora_r: 64 lora_alpha: 64 peft_use_rslora: true lora_dropout: 0.0 freeze_mm_modules: true lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj' &#32; max_grad_norm: 1.0 bf16: auto tf32: true sdp_attention: true flash_attention: false gradient_checkpointing: true</code></pre> </div> </details> <details> <summary>Stage 4 — On-Policy Multi-Outcome SFT Config (Axolotl)</summary> <div class="gs-detail-body"> <pre><code>base_model: ApocalypseParty/G4&#45;31B&#45;r4b100&#45;GRPO&#45;rp100 &#35; stage 3 output &#32; plugins: &#45; axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin &#45; axolotl.integrations.liger.LigerPlugin liger_layer_norm: true liger_rope: true liger_rms_norm: true liger_glu_activation: true liger_rms_norm_gated: true strict: false cut_cross_entropy: true &#32; datasets: &#45; path: ./data/g4_onpolicy_rp_masked.jsonl val_set_size: 0 output_dir: ./G4&#45;31B&#45;r4b100&#45;GRPO&#45;rp100&#45;sft &#32; sequence_len: 8192 pad_to_sequence_len: true sample_packing: true &#32; adapter: lora lora_r: 64 lora_alpha: 64 peft_use_rslora: false lora_dropout: 0.0 freeze_mm_modules: true lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj' &#32; gradient_accumulation_steps: 2 micro_batch_size: 1 num_epochs: 1 optimizer: adamw_torch_fused lr_scheduler: cosine learning_rate: 4e&#45;5 max_grad_norm: 1.0 warmup_ratio: 0.1 weight_decay: 0.05 saves_per_epoch: 2 &#32; bf16: auto tf32: true &#32; &#35; FA2 not supported sdp_attention: true flash_attention: false &#32; fsdp_config: fsdp_version: 2 offload_params: false cpu_ram_efficient_loading: false auto_wrap_policy: TRANSFORMER_BASED_WRAP transformer_layer_cls_to_wrap: Gemma4TextDecoderLayer state_dict_type: FULL_STATE_DICT sharding_strategy: FULL_SHARD reshard_after_forward: true activation_checkpointing: true</code></pre> </div> </details> </div> </div> </div> </body> </html>