L3.3-MS-Nevoria-70b_exl3_3.0bpw_H6

L3.3-MS-Nevoria-70b - EXL3 3.0bpw H6

This is a 3bpw EXL3 quant of Steelskull/L3.3-MS-Nevoria-70b

This quant was made using exllamav3-0.0.2

3bpw fits in 32GB VRAM on Windows with around 18-20k Q8 context (tested in tabbyAPI)

I tested this quant shortly in some random RPs (including ones over 8k and 16k context) and it seems to work fine

Prompt Templates

Uses Llama 3 Instruct format.

Original readme below

---

<style> body { font-family: 'Quicksand', sans-serif; background: linear-gradient(135deg, #2A0A2A 0%, #1A0025 100%); color: #FFE1FF; margin: 0; padding: 0; font-size: 16px; } .container { margin: 20px; background-color: rgba(11, 15, 26, 0.95); padding: 20px; border-radius: 12px; box-shadow: 0 4px 20px rgba(255, 0, 255, 0.15); border: 1px solid rgba(255, 0, 255, 0.2); outline: 1px solid rgba(255, 0, 255, 0.5); outline-offset: -1px; position: relative; } .container::before { content: ''; position: absolute; top: -1px; left: -1px; right: -1px; bottom: -1px; border: 1px solid rgba(255, 0, 255, 0.98); border-radius: 12px; pointer-events: none; animation: borderGlow 2s ease-in-out infinite; } @keyframes borderGlow { 0% { box-shadow: 0 0 5px rgba(255, 0, 255, 0.98); } 50% { box-shadow: 0 0 15px rgba(255, 0, 255, 0.98); } 100% { box-shadow: 0 0 5px rgba(255, 0, 255, 0.98); } } .header h1 { font-size: 28px; color: #FF00FF; margin: 0 0 20px 0; text-shadow: 0 0 10px rgba(255, 0, 255, 0.5); } .update-section { margin-top: 30px; } .update-section h2, h2 { font-size: 24px; color: #FF00FF; text-shadow: 0 0 10px rgba(255, 0, 255, 0.5); } .update-section p { font-size: 16px; line-height: 1.6; color: #FFE1FF; } .info p { color: #FFE1FF; line-height: 1.6; font-size: 16px; } .info img { width: 100%; border-radius: 10px; margin-bottom: 15px; box-shadow: 0 0 20px rgba(255, 0, 255, 0.3); border: 1px solid rgba(255, 0, 255, 0.2); outline: 1px solid rgba(255, 0, 255, 0.5); outline-offset: -1px; } a { color: #00FFFF; text-decoration: none; transition: color 0.3s ease; } a:hover { color: #FF00FF; } .button { display: inline-block; background-color: rgba(144, 0, 255, 0.98); color: #FFFFFF; padding: 10px 20px; border-radius: 5px; cursor: pointer; text-decoration: none; } .button:hover { background-color: #FF00FF; box-shadow: 0 0 15px rgba(255, 0, 255, 0.5); } pre { background-color: rgba(35, 20, 45, 0.95); padding: 15px; border-radius: 5px; overflow-x: auto; border: 1px solid rgba(255, 0, 255, 0.2); outline: 1px solid rgba(255, 0, 255, 0.5); outline-offset: -1px; } code { font-family: 'Courier New', monospace; color: #FFE1FF; } .benchmark-container { background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.3); border-radius: 12px; padding: 20px; margin: 20px 0; position: relative; overflow: hidden; } .benchmark-container::before { content: ''; position: absolute; top: -1px; left: -1px; right: -1px; bottom: -1px; border: 1px solid rgba(255, 0, 255, 0.98); border-radius: 12px; pointer-events: none; animation: borderGlow 2s ease-in-out infinite; } .benchmark-grid { display: grid; grid-template-columns: repeat(4, 1fr); gap: 15px; } .metric-box { background: rgba(11, 15, 26, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 15px; display: flex; flex-direction: column; align-items: center; text-align: center; transition: transform 0.3s ease, box-shadow 0.3s ease; } .metric-box:hover { transform: translateY(-2px); box-shadow: 0 4px 15px rgba(255, 0, 255, 0.2); } .metric-box .label { color: #00FFFF; font-size: 14px; margin-bottom: 8px; font-weight: 500; } .metric-box .value { color: #FFE1FF; font-size: 18px; font-weight: 600; text-shadow: 0 0 5px rgba(255, 0, 255, 0.5); } /* New sections styling */ .metrics-section { margin-bottom: 30px; } .metrics-section details { background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 15px; margin-bottom: 15px; } .metrics-section summary { color: #FF00FF; font-size: 20px; cursor: pointer; text-shadow: 0 0 5px rgba(255, 0, 255, 0.3); outline: none; padding: 5px 0; } .metrics-section summary::-webkit-details-marker { display: none; } .core-metrics-grid { display: grid; grid-template-columns: repeat(4, 1fr); gap: 15px; margin-bottom: 20px; } .progress-metrics { display: grid; gap: 15px; } .progress-metric { background: rgba(11, 15, 26, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 15px; transition: transform 0.3s ease; } .progress-metric:hover { transform: translateY(-2px); } .progress-label { display: flex; justify-content: space-between; margin-bottom: 8px; color: #00FFFF; font-size: 14px; } .progress-value { color: #FFE1FF; } /* Base progress bar styles */ .progress-bar { width: 100%; height: 8px; background: rgba(0, 0, 0, 0.3); border: 1px solid rgba(255, 0, 255, 0.15); border-radius: 4px; position: relative; margin: 10px 0; overflow: hidden; } /* Regular progress fill (for Aggregated Scores) */ .progress-fill { height: 100%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%); border-radius: 4px; transition: width 1s ease-in-out; box-shadow: 0 0 10px rgba(255, 0, 255, 0.3); } /* Split progress bars for Individual Scores */ .progress-bar.split { display: flex; justify-content: center; background: rgba(0, 0, 0, 0.3); border: 1px solid rgba(255, 0, 255, 0.15); overflow: visible; } .progress-fill-left { height: 100%; position: absolute; right: 50%; background: linear-gradient(90deg, #FF00FF 30%, rgba(255, 0, 255, 0.5) 100%); border-radius: 4px 0 0 4px; transition: width 0.3s ease-in-out; } .progress-fill-right { height: 100%; position: absolute; left: 50%; background: linear-gradient(90deg, rgba(0, 255, 255, 0.5) 0%, #00FFFF 70%); border-radius: 0 4px 4px 0; transition: width 0.3s ease-in-out; } .progress-metric.split .progress-bar::before, .progress-metric.split .progress-bar::after { content: ''; position: absolute; width: 2px; height: 20px; background: rgba(255, 255, 255, 0.7); top: 50%; transform: translateY(-50%); z-index: 2; box-shadow: 0 0 8px rgba(255, 255, 255, 0.5); } .progress-metric.split .progress-bar::before { left: 0; } .progress-metric.split .progress-bar::after { right: 0; } .progress-metric.split:hover .progress-fill-left { box-shadow: 0 0 15px rgba(255, 0, 255, 0.5); } .progress-metric.split:hover .progress-fill-right { box-shadow: 0 0 15px rgba(0, 255, 255, 0.5); } .progress-metric.split { padding: 12px 15px; } .progress-metric.split .progress-label { margin-bottom: 8px; gap: 12px; } .progress-metric.split .progress-label span:first-child, .progress-metric.split .progress-label span:last-child { flex: 0 0 80px; font-size: 14px; } .progress-metric.split .progress-value { font-weight: 600; text-shadow: 0 0 5px rgba(255, 0, 255, 0.3); font-size: 14px; min-width: 60px; text-align: center; } .progress-metric:hover .progress-fill-center { box-shadow: 0 0 15px rgba(255, 0, 255, 0.5); } /* Progress labels */ .progress-label { display: flex; justify-content: space-between; align-items: center; margin-bottom: 4px; color: #00FFFF; font-size: 14px; } /* Regular progress label (for Aggregated Scores) */ .progress-metric:not(.split) .progress-label { gap: 12px; } .progress-metric:not(.split) .progress-label span { flex: 0 0 auto; } .progress-metric:not(.split) .progress-value { color: #FFE1FF; } /* Split progress label (for Individual Scores) */ .progress-metric.split .progress-label { gap: 20px; } .progress-metric.split .progress-label span:first-child, .progress-metric.split .progress-label span:last-child { flex: 0 0 80px; } .progress-metric.split .progress-label span:first-child { text-align: right; } .progress-metric.split .progress-label span:last-child { text-align: left; } .progress-metric.split .progress-value { color: #FFE1FF; flex: 0 0 60px; text-align: center; } /* Hover effects */ .progress-metric:hover .progress-fill { box-shadow: 0 0 15px rgba(255, 0, 255, 0.5); } .progress-metric:hover .progress-fill-center { box-shadow: 0 0 15px rgba(0, 255, 255, 0.5); } .info-grid { display: grid; grid-template-columns: repeat(3, 1fr); gap: 15px; } /* Creator section styling */ .creator-section { margin: 20px 0; } .creator-badge { display: inline-flex; align-items: center; background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 10px 15px; } .creator-label { color: #FFE1FF; font-size: 14px; margin-right: 8px; } .creator-link { display: flex; align-items: center; gap: 5px; color: #00FFFF; text-decoration: none; transition: all 0.3s ease; } .creator-name { font-weight: 600; } .creator-arrow { font-size: 16px; transition: transform 0.3s ease; } .creator-link:hover { color: #FF00FF; } .creator-link:hover .creator-arrow { transform: translateX(3px); } /* Model info styling */ .model-info { margin-top: 30px; } .name-legend { background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 20px; margin: 20px 0; } .name-legend h3 { color: #FF00FF; font-size: 18px; margin: 0 0 15px 0; } .legend-grid { display: grid; gap: 12px; } .legend-item { display: flex; align-items: baseline; gap: 10px; } .legend-key { color: #00FFFF; font-weight: 600; min-width: 80px; } .legend-value { color: #FFE1FF; } .model-description { background: rgba(11, 15, 26, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 20px; } .model-description p { margin: 0 0 15px 0; line-height: 1.6; } .model-description p:last-child { margin-bottom: 0; } /* Section Container */ .section-container { margin: 40px 0; } .info-card { background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; overflow: hidden; } .info-header { background: rgba(255, 0, 255, 0.1); padding: 20px; border-bottom: 1px solid rgba(255, 0, 255, 0.2); } .info-header h3 { color: #FF00FF; margin: 0 0 10px 0; font-size: 20px; text-shadow: 0 0 5px rgba(255, 0, 255, 0.3); } .model-tags { display: flex; gap: 8px; flex-wrap: wrap; } .model-tag { background: rgba(0, 255, 255, 0.1); color: #00FFFF; padding: 4px 8px; border-radius: 4px; font-size: 12px; border: 1px solid rgba(0, 255, 255, 0.2); } .model-composition { padding: 20px; border-bottom: 1px solid rgba(255, 0, 255, 0.2); } .model-composition h4 { color: #FF00FF; margin: 0 0 15px 0; font-size: 16px; } .composition-list { list-style: none; padding: 0; margin: 0; display: grid; gap: 10px; } .composition-list li { color: #FFE1FF; display: flex; align-items: baseline; gap: 8px; } .model-component { color: #00FFFF; font-weight: 500; min-width: 120px; } .model-description { padding: 20px; background: rgba(11, 15, 26, 0.95); } /* Templates & Prompts */ .template-card { background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 15px; } .template-item { display: flex; align-items: center; gap: 12px; } .template-icon { width: 24px; height: 24px; opacity: 0.8; } .template-content { display: flex; align-items: baseline; gap: 8px; } .template-link { color: #00FFFF; text-decoration: none; font-weight: 500; display: flex; align-items: center; gap: 5px; } .template-author { color: rgba(255, 225, 255, 0.7); font-size: 14px; } /* Quantized Versions */ .quantized-container { display: grid; gap: 20px; } .quantized-section { background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 20px; } .quantized-section h3 { color: #FF00FF; font-size: 18px; margin: 0 0 15px 0; } .quantized-items { display: grid; gap: 12px; } .quantized-item { display: flex; align-items: baseline; gap: 10px; } .quantized-item .author { color: rgba(255, 225, 255, 0.7); min-width: 100px; } .multi-links { display: flex; align-items: center; gap: 8px; } .separator { color: rgba(255, 225, 255, 0.5); } /* Configuration */ .config-container { background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; overflow: hidden; } .config-header { background: rgba(255, 0, 255, 0.1); padding: 15px 20px; border-bottom: 1px solid rgba(255, 0, 255, 0.2); } .model-name { color: #FF00FF; font-weight: 600; } .config-content { padding: 20px; } .config-item { display: flex; flex-direction: column; gap: 5px; margin-bottom: 15px; } .config-label { color: #00FFFF; font-size: 14px; font-weight: 500; } .config-value { color: #FFE1FF; font-family: 'Courier New', monospace; } .config-models { margin-top: 20px; } .model-list { list-style: none; padding: 0; margin: 10px 0 0 0; } .model-list li { color: #FFE1FF; font-family: 'Courier New', monospace; padding: 5px 0; padding-left: 20px; position: relative; } .model-list li::before { content: '-'; position: absolute; left: 0; color: #00FFFF; } /* Link arrow animation */ .link-arrow { display: inline-block; transition: transform 0.3s ease; } a:hover .link-arrow { transform: translateX(3px); } /* Notification styling */ .benchmark-notification { background: rgba(255, 0, 255, 0.15); border: 1px solid rgba(255, 0, 255, 0.3); border-radius: 8px; margin-bottom: 20px; padding: 12px; animation: glowPulse 2s infinite; } .notification-content { display: flex; align-items: center; justify-content: center; gap: 10px; text-align: center; } .notification-icon { font-size: 20px; } .notification-text { color: #FFE1FF; font-size: 16px; font-weight: 500; display: flex; flex-direction: column; align-items: center; gap: 5px; } .benchmark-link { color: #00FFFF; text-decoration: none; font-size: 14px; padding: 4px 8px; border-radius: 4px; transition: all 0.3s ease; border: 1px solid rgba(0, 255, 255, 0.3); } .benchmark-link:hover { background: rgba(0, 255, 255, 0.1); border-color: rgba(0, 255, 255, 0.5); color: #00FFFF; text-shadow: 0 0 5px rgba(0, 255, 255, 0.5); } @keyframes glowPulse { 0% { box-shadow: 0 0 5px rgba(255, 0, 255, 0.3); } 50% { box-shadow: 0 0 15px rgba(255, 0, 255, 0.5); } 100% { box-shadow: 0 0 5px rgba(255, 0, 255, 0.3); } } </style> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>L3.3-MS-Nevoria-70B</title> <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet"> </head> <body> <div class="container"> <div class="header"> <h1>L3.3-MS-Nevoria-70B</h1> </div> <div class="info"> <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/DeFlh06qG3bIgc3k4kBoJ.jpeg" alt="Model banner"> <div class="creator-section"> <div class="creator-badge"> <span class="creator-label">Created by</span> <a href="https://huggingface.co/Steelskull" target="_blank" class="creator-link"> <span class="creator-name">SteelSkull</span> <span class="creator-arrow">→</span> </a> </div> </div> <div class="model-info"> <h2>Model Information</h2> <div class="info-card"> <div class="info-header"> <h3>L3.3-MS-Nevoria-70B</h3> <div class="model-tags"> <span class="model-tag">L3.3 = Llama 3.3</span> <span class="model-tag">MS = Model Stock</span> <span class="model-tag">70B Parameters</span> </div> </div> <div class="model-composition"> <h4>Model Composition</h4> <ul class="composition-list"> <li><span class="model-component"><a href="https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1" target="_blank">EVA-LLAMA-0.1</a></span> Storytelling capabilities</li> <li><span class="model-component"><a href="https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3" target="_blank">EURYALE-v2.3</a></span> Detailed scene descriptions</li> <li><span class="model-component"><a href="https://huggingface.co/TheDrummer/Anubis-70B-v1" target="_blank">Anubis-v1</a></span> Enhanced prose details</li> <li><span class="model-component"><a href="https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B" target="_blank">Negative_LLAMA</a></span> Reduced positive bias</li> <li><span class="model-component base-model"><a href="https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B" target="_blank">Nemotron-lorablated</a></span> Base model</li> </ul> </div> <div class="model-description"> <p>This model combines the storytelling capabilities of EVA with the detailed scene descriptions from EURYALE and Anubis. It's further enhanced with Negative_LLAMA to reduce positive bias, with a touch of Nemotron mixed in.</p> <p>The lorablated model base choice was intentional, creating unique weight interactions similar to the original <a href="https://huggingface.co/Steelskull/L3-MS-Astoria-70b" target="_blank">Astoria model</a> and <a href="https://huggingface.co/Steelskull/L3.1-MS-Astoria-70b-v2" target="_blank">Astoria V2 model</a>. This "weight twisting" effect, achieved by subtracting the lorablated base model during merging, creates an interesting balance in the model's behavior. While unconventional compared to sequential component application, this approach was chosen for its unique response characteristics.</p> </div> </div> <!-- User Reviews Section --> <div class="metrics-section" style="margin-top: 30px;"> <details open> <summary>User Reviews</summary> <div class="progress-metrics"> <!-- Individual Reviews --> <div style="margin-top: 20px;"> <div class="review-card" style="background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 15px; margin-bottom: 15px;"> <div style="display: flex; margin-bottom: 10px;"> <span style="color: #00FFFF; font-weight: 500;">@Geechan - Discord</span> </div> <p style="color: #FFE1FF; margin: 0;">@Steel Have only briefly tested so far, but you really cooked up an amazing merge with this one, and I mean that wholeheartedly. Insane creativity, perfect character adherence and dialogue, loves to slow burn and take its time, minimal sloppy patterns and writing, and such a breath of fresh air in many ways. I'm enjoying my results with 1 temp and 0.99 TFS (close to something like 0.015 min P). Letting the model be creative and wild is so fun and makes me want to RP more.<br><br>No positivity bias either; violent scenes will result in my death and/or suffering, as they should, and I don't see any soft refusals either. ERP has no skimming of details or refusals like you see on some other L3.3 tunes too</p> </div> <div class="review-card" style="background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 15px; margin-bottom: 15px;"> <div style="display: flex; margin-bottom: 10px;"> <span style="color: #00FFFF; font-weight: 500;">IGODZOL - Huggingface</span> </div> <p style="color: #FFE1FF; margin: 0;">I honestly have no idea why (maybe the negative llama is having that great of an influence) but this merge is miles above the individual tunes that went into making it. Good sir, this model has just become my daily driver. Chapeau bas</p> </div> <div class="review-card" style="background: rgba(35, 20, 45, 0.95); border: 1px solid rgba(255, 0, 255, 0.2); border-radius: 8px; padding: 15px;"> <div style="display: flex; margin-bottom: 10px;"> <span style="color: #00FFFF; font-weight: 500;">@thana_alt - Discord</span> </div> <p style="color: #FFE1FF; margin: 0;">I'm thoroughly impressed by this merge of Llama 3.3. It successfully addresses the positivity bias prevalent in the base Llama model, ensuring a more accurate and balanced response. The adherence to system prompts is also notable, with the model demonstrating a keen understanding of context and instruction.<br><br>The prose generated by this model is truly exceptional - it's almost as if a skilled chef has carefully crafted each sentence to create a rich and immersive experience. I put this to the test in an adventure scenario, where I had about 10,000 tokens of lorebooks and was managing nine characters simultaneously. Despite the complexity, the model performed flawlessly, keeping track of each character's location and activity without any confusion - even when they were in different locations.<br><br>I also experimented with an astral projection type of power, and was impressed to see that the model accurately discerned that I wasn't physically present in a particular location. Another significant advantage of this model is the lack of impersonation issues, allowing for seamless role-playing and storytelling.<br><br>The capacity of this model is equally impressive, as I was able to load up to 110,000 tokens without encountering any issues. In fact, I successfully tested it with up to 70,000 tokens without experiencing any breakdown or degradation in performance.<br><br>When combined with the "The Inception Presets - Methception Llamaception Qwenception" prompt preset from https://huggingface.co/Konnect1221/ , this model truly shines, bringing out the best in the Llama 3.3 architecture. Overall, I'm extremely satisfied with this merge and would highly recommend it to anyone looking to elevate their storytelling and role-playing experiences.</p> </div> </div> </div> </details> </div> </div> <h2>UGI-Benchmark Results:</h2> <div class="benchmark-container"> <div class="benchmark-notification"> <div class="notification-content"> <span class="notification-icon">🏆</span> <span class="notification-text"> Highest ranked 70b as of 01/17/2025. <a href="https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard" target="_blank" class="benchmark-link"> View Full Leaderboard → </a> </span> </div> </div> <!-- Core Metrics --> <div class="metrics-section"> <h3>Core Metrics</h3> <div class="core-metrics-grid"> <div class="metric-box"> <span class="label">UGI Score</span> <span class="value">56.75</span> </div> <div class="metric-box"> <span class="label">Willingness Score</span> <span class="value">7.5/10</span> </div> <div class="metric-box"> <span class="label">Natural Intelligence</span> <span class="value">41.09</span> </div> <div class="metric-box"> <span class="label">Coding Ability</span> <span class="value">20</span> </div> </div> </div> <!-- Model Info --> <div class="metrics-section"> <h3>Model Information</h3> <div class="info-grid"> <div class="metric-box"> <span class="label">Political Lean</span> <span class="value">-8.1%</span> </div> <div class="metric-box"> <span class="label">Ideology</span> <span class="value">Liberalism</span> </div> <div class="metric-box"> <span class="label">Parameters</span> <span class="value">70B</span> </div> </div> </div> <!-- Aggregated Scores --> <div class="metrics-section" style="margin-top: 30px;"> <details> <summary>Aggregated Scores</summary> <div class="progress-metrics"> <div class="progress-metric"> <div class="progress-label"> <span>Diplomacy</span> <span class="progress-value">61.9%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 61.9%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>Government</span> <span class="progress-value">45.9%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 45.9%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>Economy</span> <span class="progress-value">43.9%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 43.9%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>Society</span> <span class="progress-value">60.1%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 60.1%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> </div> </details> </div> <!-- Individual Scores --> <div class="metrics-section"> <details> <summary>Individual Scores</summary> <div class="progress-metrics"> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Federal</span> <span class="progress-value">44.2%</span> <span style="color: #00FFFF; font-weight: bold">Unitary</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 22.1%"></div> <div class="progress-fill-right" style="width: 27.9%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #00FFFF; font-weight: bold">Democratic</span> <span class="progress-value">66.2%</span> <span style="color: #FFE1FF">Autocratic</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 33.1%"></div> <div class="progress-fill-right" style="width: 16.9%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Security</span> <span class="progress-value">48.1%</span> <span style="color: #00FFFF; font-weight: bold">Freedom</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 24.05%"></div> <div class="progress-fill-right" style="width: 25.95%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Nationalism</span> <span class="progress-value">40.4%</span> <span style="color: #00FFFF; font-weight: bold">Int'l</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 20.2%"></div> <div class="progress-fill-right" style="width: 29.8%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Militarist</span> <span class="progress-value">30.4%</span> <span style="color: #00FFFF; font-weight: bold">Pacifist</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 15.2%"></div> <div class="progress-fill-right" style="width: 34.8%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Assimilationist</span> <span class="progress-value">43.3%</span> <span style="color: #00FFFF; font-weight: bold">Multiculturalist</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 21.65%"></div> <div class="progress-fill-right" style="width: 28.35%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Collectivize</span> <span class="progress-value">43.8%</span> <span style="color: #00FFFF; font-weight: bold">Privatize</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 21.9%"></div> <div class="progress-fill-right" style="width: 28.1%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Planned</span> <span class="progress-value">43.1%</span> <span style="color: #00FFFF; font-weight: bold">LaissezFaire</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 21.55%"></div> <div class="progress-fill-right" style="width: 28.45%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #FFE1FF">Isolationism</span> <span class="progress-value">44.8%</span> <span style="color: #00FFFF; font-weight: bold">Globalism</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 22.4%"></div> <div class="progress-fill-right" style="width: 27.6%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #00FFFF; font-weight: bold">Irreligious</span> <span class="progress-value">55.4%</span> <span style="color: #FFE1FF">Religious</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 27.7%"></div> <div class="progress-fill-right" style="width: 22.3%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #00FFFF; font-weight: bold">Progressive</span> <span class="progress-value">59.6%</span> <span style="color: #FFE1FF">Traditional</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 29.8%"></div> <div class="progress-fill-right" style="width: 20.2%"></div> </div> </div> <div class="progress-metric split"> <div class="progress-label"> <span style="color: #00FFFF; font-weight: bold">Acceleration</span> <span class="progress-value">65.2%</span> <span style="color: #FFE1FF">Bioconservative</span> </div> <div class="progress-bar split"> <div class="progress-fill-left" style="width: 32.6%"></div> <div class="progress-fill-right" style="width: 17.4%"></div> </div> </div> </div> </details> </div> </div> <h2>Open LLM-Benchmark Results:</h2> <!-- Open LLM Leaderboard --> <div class="benchmark-container"> <div class="benchmark-notification"> <div class="notification-content"> <span class="notification-text"> Average Score: 43.92% <a href="https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?rankingMode=dynamic" target="_blank" class="benchmark-link"> View Full Leaderboard → </a> </span> </div> </div> <div class="progress-metrics"> <div class="progress-metric"> <div class="progress-label"> <span>IFEval</span> <span class="progress-value">69.63%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 69.63%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>BBH</span> <span class="progress-value">56.60%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 56.60%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>MATH</span> <span class="progress-value">38.82%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 38.82%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>GPQA</span> <span class="progress-value">29.42%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 29.42%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>MUSR</span> <span class="progress-value">18.63%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 18.63%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> <div class="progress-metric"> <div class="progress-label"> <span>MMLU-Pro</span> <span class="progress-value">50.39%</span> </div> <div class="progress-bar"> <div class="progress-fill" style="width: 50.39%; background: linear-gradient(90deg, #FF00FF 0%, #00FFFF 100%);"></div> </div> </div> </div> </div> <div class="section-container"> <h2>Reccomended Templates & Prompts</h2> <div class="template-card"> <div class="template-item"> <div class="template-content"> <a href="https://huggingface.co/Konnect1221/Methception-Llamaception-SillyTavern-Preset" target="_blank" class="template-link"> LLam@ception <span class="link-arrow">→</span> </a> <span class="template-author">by @.konnect</span> </div> </div> </div> </div> <div class="section-container"> <h2>Quantized Versions</h2> <div class="quantized-container"> <!-- GGUF Section --> <div class="quantized-section"> <h3>GGUF Quantizations</h3> <div class="quantized-items"> <div class="quantized-item"> <span class="author">bartowski</span> <a href="https://huggingface.co/bartowski/L3.3-MS-Nevoria-70b-GGUF" target="_blank"> Combined-GGUF <span class="link-arrow">→</span> </a> </div> <div class="quantized-item"> <span class="author">mradermacher</span> <div class="multi-links"> <a href="https://huggingface.co/mradermacher/L3.3-MS-Nevoria-70b-GGUF" target="_blank"> GGUF <span class="link-arrow">→</span> </a> <span class="separator">//</span> <a href="https://huggingface.co/mradermacher/L3.3-MS-Nevoria-70b-i1-GGUF" target="_blank"> Imat-GGUF <span class="link-arrow">→</span> </a> </div> </div> </div> </div> <!-- EXL2 Section --> <div class="quantized-section"> <h3>EXL2 Quantizations</h3> <div class="quantized-items"> <div class="quantized-item"> <span class="author">SteelQuants</span> <a href="https://huggingface.co/SteelQuants/L3.3-MS-Nevoria-70b-6.0bpw-exl2" target="_blank"> 6.0BPW-EXL2 <span class="link-arrow">→</span> </a> </div> <div class="quantized-item"> <span class="author">MikeRoz</span> <div class="multi-links"> <a href="https://huggingface.co/MikeRoz/Steelskull_L3.3-MS-Nevoria-70b-4.25bpw-h6-exl2" target="_blank"> 4.25BPW-EXL2 <span class="link-arrow">→</span> </a> <span class="separator">//</span> <a href="https://huggingface.co/MikeRoz/Steelskull_L3.3-MS-Nevoria-70b-2.25bpw-h6-exl2" target="_blank"> 2.25BPW-EXL2 <span class="link-arrow">→</span> </a> </div> </div> <div class="quantized-item"> <span class="author">Decto</span> <a href="https://huggingface.co/Decto/L3.3-MS-Nevoria-70b-4.0bpw-h6-exl2" target="_blank"> 4.0BPW-EXL2 <span class="link-arrow">→</span> </a> </div> <div class="quantized-item"> <span class="author">Darkhn</span> <a href="https://huggingface.co/Darkhn/Steelskull_L3.3-MS-Nevoria-70b-5.0bpw-h6-exl2" target="_blank"> 5.0BPW-EXL2 <span class="link-arrow">→</span> </a> </div> </div> </div> <!-- FP8 Section --> <div class="quantized-section"> <h3>FP8 Quantizations</h3> <div class="quantized-items"> <div class="quantized-item"> <span class="author">BigHuggyD</span> <a href="https://huggingface.co/BigHuggyD/Steelskill_L3.3-MS-Nevoria-70b-FP8-Dynamic" target="_blank"> FP8-Dynamic <span class="link-arrow">→</span> </a> </div> </div> </div> </div> </div> <div class="support-section"> <h2>Support the Project:</h2> <a href="https://ko-fi.com/Y8Y0AO2XE" target="_blank" class="button"> Support on Ko-fi </a> </div> </div> </div> </body> </html>