Lilitu-L3.3-70b-0.1

This 70B parameter model is my first merge of some of my favorite models for storytelling and RP:

<ul> <li><a href="https://huggingface.co/BruhzWater/Sapphira-L3.3-70b-0.2">BruhzWater/Sapphira-L3.3-70b-0.2</a></li> <li><a href="https://huggingface.co/sophosympatheia/Strawberrylemonade-L3-70B-v1.2">sophosympatheia/Strawberrylemonade-L3-70B-v1.2</a></li> <li><a href="https://huggingface.co/BruhzWater/Edens-Fall-L3.3-70b-0.3c">BruhzWater/Edens-Fall-L3.3-70b-0.3c</a></li> </ul>

<b>You are encouraged to try these great models individually as well.</b> Thanks to the creators of these models and merges and also thanks to <a href="https://huggingface.co/TheDrummer">TheDrummer</a> for <a href="https://huggingface.co/TheDrummer/Anubis-70B-v1.1">Anubis</a> (part of the Sapphira merge).

<h2>Quantizations</h2> <ul> <li>EXL3 4bpw: <a href="https://huggingface.co/Ionze/Lilitu-L3.3-70b-0.1-exl3-4bpw">https://huggingface.co/Ionze/Lilitu-L3.3-70b-0.1-exl3-4bpw</a></li> <li>EXL3 4.25bpw: <a href="https://huggingface.co/Ionze/Lilitu-L3.3-70b-0.1-exl3-4.25bpw">https://huggingface.co/Ionze/Lilitu-L3.3-70b-0.1-exl3-4.25bpw</a></li> <li>EXL3 4.5bpw: <a href="https://huggingface.co/Ionze/Lilitu-L3.3-70b-0.1-exl3-4.5bpw">https://huggingface.co/Ionze/Lilitu-L3.3-70b-0.1-exl3-4.5bpw</a></li> </ul>

By mradermacher:

<ul> <li>Static quants: <a href="https://huggingface.co/mradermacher/Lilitu-L3.3-70b-0.1-GGUF">https://huggingface.co/mradermacher/Lilitu-L3.3-70b-0.1-GGUF</a></li> <li>iMatrix quants: <a href="https://huggingface.co/mradermacher/Lilitu-L3.3-70b-0.1-i1-GGUF">https://huggingface.co/mradermacher/Lilitu-L3.3-70b-0.1-i1-GGUF</a></li> </ul> <h2> <span> Chat and Instruct Template: </span> </h2> <p>Llama3 Instruct</p> <h2><p>My settings:</p></h2> <pre><code>Temp: 1 Min P: 0.03 Top P: 0.9 Top K: 0 Typical_P: 1 Repetition Penalty: 1.05 Rep Pen Range: 4096 XTC Threshold: 0.1 XTC Probability: 0 DRY Multiplier: 0.8 DRY Base: 1.8 DRY Allowed Length: 3 Dry Penalty Range: 4096 </code></pre> Or use the provided <a href="https://huggingface.co/Ionze/Lilitu-L3.3-70b-0.1/resolve/main/presets/ST-Lilitu-L3.3-70b.json">ST presets</a> <h2><p>Merge configuration:</P></h2> <pre><code> models: - model: ./Sapphira-L3.3-70b-0.2 parameters: weight: 0.55 density: 0.6 - model: ./Strawberrylemonade-L3-70B-v1.2 parameters: weight: 0.25 density: 0.4 - model: ./Edens-Fall-L3.3-70b-0.3c parameters: weight: 0.15 density: 0.3 merge_method: della base_model: ./Sapphira-L3.3-70b-0.2 parameters: epsilon: 0.08 lambda: 0.85 normalize: true dtype: bfloat16 </code></pre>