@@ -1,199 +1,377 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+base_model:
+- zerofata/L3.3-GeneticLemonade-Final-v2-70B
+- zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B
+- deepcogito/cogito-v1-preview-llama-70B
+- arcee-ai/Arcee-SuperNova-v1
 library_name: transformers
+tags:
+- mergekit
+- merge
+- not-for-all-audiences
+- heretic
+- uncensored
+- decensored
+- abliterated
+license: llama3
+language:
+- en
 ---
+# This is a decensored version of [sophosympatheia/Strawberrylemonade-L3-70B-v1.2](https://huggingface.co/sophosympatheia/Strawberrylemonade-L3-70B-v1.2), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0
+## Abliteration parameters
+| Parameter | Value |
+| :-------- | :---: |
+| **direction_index** | 68.22 |
+| **attn.o_proj.max_weight** | 0.86 |
+| **attn.o_proj.max_weight_position** | 47.60 |
+| **attn.o_proj.min_weight** | 0.28 |
+| **attn.o_proj.min_weight_distance** | 5.39 |
+| **mlp.down_proj.max_weight** | 1.11 |
+| **mlp.down_proj.max_weight_position** | 51.74 |
+| **mlp.down_proj.min_weight** | 0.83 |
+| **mlp.down_proj.min_weight_distance** | 38.68 |
+## Performance
+| Metric | This model | Original model ([sophosympatheia/Strawberrylemonade-L3-70B-v1.2](https://huggingface.co/sophosympatheia/Strawberrylemonade-L3-70B-v1.2)) |
+| :----- | :--------: | :---------------------------: |
+| **KL divergence** | 0.0345 | 0 *(by definition)* |
+| **Refusals** | 18/100 | 99/100 |
+-----
+# <span style="color: #EC4899; text-align: center; display: block; font-size: 2.5rem; margin-bottom: 1em; text-shadow: 0 0 10px rgba(236, 72, 153, 0.3);">StrawberryLemonade-L3-70B-v1.2</span>
+<div style="background: linear-gradient(to bottom, rgba(236, 72, 153, 0.05), rgba(26, 31, 46, 0.8)); border: 1px solid rgba(236, 72, 153, 0.3); border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 5px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.9;"></div>
+  <img src="https://i.imgur.com/XRqSQwk.png" alt="StrawberryLemonade" style="width: 80%; min-width: 400px; display: block; margin: auto; border-radius: 8px; margin-bottom: 1.5em;">
+  <p style="color: #D1D5DB; margin-bottom: 1em;">This 70B parameter model is a merge of <a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Final-v2-70B" style="color: #EC4899; text-decoration: none; border-bottom: 1px dotted rgba(236, 72, 153, 0.4);">zerofata/L3.3-GeneticLemonade-Final-v2-70B</a> and <a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B" style="color: #EC4899; text-decoration: none; border-bottom: 1px dotted rgba(236, 72, 153, 0.4);">zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B</a>, which are two excellent models for roleplaying, on top of two different base models that were then combined into this model. In my opinion, this merge improves upon my previous release (v1.0) with enhanced creativity and expressiveness.</p>
+  <p style="color: #EC4899; font-weight: 600; margin-bottom: 1em;">This model is uncensored. <em>You are responsible for whatever you do with it.</em></p>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">This model was designed for roleplaying and storytelling and I think it does well at both. It may also perform well at other tasks but I have not tested its performance in other areas.</p>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Versions</span>
+<div style="background-color: #1a1f2e; border: 1px solid #2d3748; border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 4px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.7;"></div>
+  <table style="width: 100%; border-collapse: collapse; color: #D1D5DB;">
+    <thead>
+      <tr>
+        <th style="width: 50%; color: #EC4899; font-weight: 600; text-align: left; padding-bottom: 12px; border-bottom: 2px solid rgba(236, 72, 153, 0.3);">Model</th>
+        <th style="width: 50%; color: #EC4899; font-weight: 600; text-align: left; padding-bottom: 12px; border-bottom: 2px solid rgba(236, 72, 153, 0.3);">Description</th>
+      </tr>
+    </thead>
+    <tbody>
+      <tr style="border-bottom: 1px solid #2d3748;">
+        <td style="padding: 12px 10px 12px 0; font-family: 'Fira Code', 'Courier New', Courier, monospace; color: #e1e7ef;">StrawberryLemonade-L3-70B-v1.0</td>
+        <td style="padding: 12px 0 12px 10px;">The original version. I think v1.1 and v1.2 are both improvements.</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #2d3748;">
+        <td style="padding: 12px 10px 12px 0; font-family: 'Fira Code', 'Courier New', Courier, monospace; color: #e1e7ef;">StrawberryLemonade-L3-70B-v1.1</td>
+        <td style="padding: 12px 0 12px 10px;">This is my favorite version right now. I like its writing voice and creativity. It's great fun.</td>
+      </tr>
+      <tr>
+        <td style="padding: 12px 10px 12px 0; font-family: 'Fira Code', 'Courier New', Courier, monospace; color: #e1e7ef;">StrawberryLemonade-L3-70B-v1.2</td>
+        <td style="padding: 12px 0 12px 10px;">This version is tamer than v1.1 and easier to control. Outputs are more predictable and its writing voice is more formal.</td>
+      </tr>
+    </tbody>
+  </table>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Known Issues</span>
+<div style="background-color: #1a1f2e; border: 1px solid #2d3748; border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 4px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.7;"></div>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">None so far.</p>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Sampler Tips</span>
+<div style="background-color: #1a1f2e; border: 1px solid #2d3748; border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 4px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.7;"></div>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">This model seems to be highly responsive to variations in temperature and min-p, which you can use to good effect.</p>
+  <h3 style="color: #e1e7ef; font-size: 1.4rem; margin-top: 1.5em; margin-bottom: 0.5em;">Reliable Settings</h3>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">This combination will produce more reliable and coherent responses. Use this if you prefer a 'serious' tone or just don't want to reroll responses very often.</p>
+  <ul style="color: #D1D5DB; margin-bottom: 1em; padding-left: 20px;">
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">Min-P:</span> 0.08 - 0.1</li>
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">Dynamic Temperature:</span> 0.9 - 1.15</li>
+  </ul>
+  <p style="color: #D1D5DB; margin-bottom: 1em; text-align: center;">OR</p>
+  <ul style="color: #D1D5DB; margin-bottom: 1em; padding-left: 20px;">
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">Min-P:</span> 0.05</li>
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">Temperature:</span> 1.0</li>
+  </ul>
+  <h3 style="color: #e1e7ef; font-size: 1.4rem; margin-top: 1.5em; margin-bottom: 0.5em;">Creative Settings</h3>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">This combination will unleash more creativity, but you may have to reroll more often to fix coherency issues.</p>
+  <ul style="color: #D1D5DB; margin-bottom: 1em; padding-left: 20px;">
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">Min-P:</span> <= 0.05</li>
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">Dynamic Temperature:</span> 0.9 - 1.2</li>
+  </ul>
+  <h3 style="color: #e1e7ef; font-size: 1.4rem; margin-top: 1.5em; margin-bottom: 0.5em;">General Settings</h3>
+    <ul style="color: #D1D5DB; margin-bottom: 1em; padding-left: 20px;">
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">Rep Penalty:</span> You don't need that much. 1.05 over 4096 tokens works for me.</li>
+    <li style="margin-bottom: 0.5em;"><span style="color: #EC4899; font-weight: 600;">DRY:</span> 0.8 multiplier, 1.8 base, 3-4 allowed length</li>
+  </ul>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">Experiment with any and all of the settings below! What suits my preferences may not suit yours.</p>
+  <details style="margin-bottom: 20px; background-color: #111827; border-radius: 8px; overflow: hidden; border: 1px solid #2d3748;">
+    <summary style="padding: 12px 15px; cursor: pointer; background-color: #1a1f2e; border-bottom: 1px solid #2d3748; font-weight: 600; color: #EC4899; display: flex; align-items: center;">Recommended Settings JSON (Silly Tavern)</summary>
+    <div style="padding: 15px;">
+     <p style="color: #D1D5DB; margin-bottom: 1em;">If you save the below settings as a .json file, you can import them directly into Silly Tavern. Adjust settings as needed, especially the context length.</p>
+      <pre style="background-color: rgba(0, 0, 0, 0.2); border-radius: 6px; padding: 15px; overflow-x: auto; border: 1px solid #2d3748; position: relative;"><code style="font-family: 'Fira Code', 'Courier New', Courier, monospace; font-size: 0.9em; color: #e1e7ef;">{
+    "temp": 1,
+    "temperature_last": true,
+    "top_p": 1,
+    "top_k": 0,
+    "top_a": 0,
+    "tfs": 1,
+    "epsilon_cutoff": 0,
+    "eta_cutoff": 0,
+    "typical_p": 1,
+    "min_p": 0.1,
+    "rep_pen": 1.05,
+    "rep_pen_range": 4096,
+    "rep_pen_decay": 0,
+    "rep_pen_slope": 1,
+    "no_repeat_ngram_size": 0,
+    "penalty_alpha": 0,
+    "num_beams": 1,
+    "length_penalty": 1,
+    "min_length": 0,
+    "encoder_rep_pen": 1,
+    "freq_pen": 0,
+    "presence_pen": 0,
+    "skew": 0,
+    "do_sample": true,
+    "early_stopping": false,
+    "dynatemp": true,
+    "min_temp": 0.9,
+    "max_temp": 1.2,
+    "dynatemp_exponent": 1,
+    "smoothing_factor": 0,
+    "smoothing_curve": 1,
+    "dry_allowed_length": 4,
+    "dry_multiplier": 0.8,
+    "dry_base": 1.8,
+    "dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
+    "dry_penalty_last_n": 0,
+    "add_bos_token": true,
+    "ban_eos_token": false,
+    "skip_special_tokens": false,
+    "mirostat_mode": 0,
+    "mirostat_tau": 2,
+    "mirostat_eta": 0.1,
+    "guidance_scale": 1,
+    "negative_prompt": "",
+    "grammar_string": "",
+    "json_schema": {},
+    "banned_tokens": "",
+    "sampler_priority": [
+        "repetition_penalty",
+        "dry",
+        "presence_penalty",
+        "top_k",
+        "top_p",
+        "typical_p",
+        "epsilon_cutoff",
+        "eta_cutoff",
+        "tfs",
+        "top_a",
+        "min_p",
+        "mirostat",
+        "quadratic_sampling",
+        "dynamic_temperature",
+        "frequency_penalty",
+        "temperature",
+        "xtc",
+        "encoder_repetition_penalty",
+        "no_repeat_ngram"
+    ],
+    "samplers": [
+        "penalties",
+        "dry",
+        "top_n_sigma",
+        "top_k",
+        "typ_p",
+        "tfs_z",
+        "typical_p",
+        "top_p",
+        "min_p",
+        "xtc",
+        "temperature"
+    ],
+    "samplers_priorities": [
+        "dry",
+        "penalties",
+        "no_repeat_ngram",
+        "temperature",
+        "top_nsigma",
+        "top_p_top_k",
+        "top_a",
+        "min_p",
+        "tfs",
+        "eta_cutoff",
+        "epsilon_cutoff",
+        "typical_p",
+        "quadratic",
+        "xtc"
+    ],
+    "ignore_eos_token": false,
+    "spaces_between_special_tokens": true,
+    "speculative_ngram": false,
+    "sampler_order": [
+        6,
+        0,
+        1,
+        3,
+        4,
+        2,
+        5
+    ],
+    "logit_bias": [],
+    "xtc_threshold": 0,
+    "xtc_probability": 0,
+    "nsigma": 0,
+    "min_keep": 0,
+    "ignore_eos_token_aphrodite": false,
+    "spaces_between_special_tokens_aphrodite": true,
+    "rep_pen_size": 0,
+    "genamt": 1000,
+    "max_length": 16384
+}</code></pre>
+    </div>
+  </details>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Prompting Tips</span>
+<div style="background-color: #1a1f2e; border: 1px solid #2d3748; border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 4px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.7;"></div>
+  <details style="margin-bottom: 20px; background-color: #111827; border-radius: 8px; overflow: hidden; border: 1px solid #2d3748;">
+    <summary style="padding: 12px 15px; cursor: pointer; background-color: #1a1f2e; border-bottom: 1px solid #2d3748; font-weight: 600; color: #EC4899; display: flex; align-items: center;">Instruct Template (Silly Tavern)</summary>
+    <div style="padding: 15px;">
+      <p style="color: #D1D5DB; margin-bottom: 1em;">If you save this as a .json file, you can import it directly into Silly Tavern.</p>
+      <p style="color: #D1D5DB; margin-bottom: 1em;">If you have problems with the model impersonating the user or other characters in a group chat and you want to suppress that behavior, override the last_output_sequence line as shown in the JSON below to be very clear about that requirement. If you don't need it, remove it.</p>
+      <pre style="background-color: rgba(0, 0, 0, 0.2); border-radius: 6px; padding: 15px; overflow-x: auto; border: 1px solid #2d3748; position: relative;"><code style="font-family: 'Fira Code', 'Courier New', Courier, monospace; font-size: 0.9em; color: #e1e7ef;">{
+    "wrap": false,
+    "system_sequence": "<|start_header_id|>system<|end_header_id|>\\n\\nSystem: ",
+    "stop_sequence": "<|eot_id|>",
+    "input_sequence": "<|start_header_id|>user<|end_header_id|>\\n\\n",
+    "output_sequence": "<|start_header_id|>assistant<|end_header_id|>\\n\\n",
+    "macro": true,
+    "system_sequence_prefix": "",
+    "system_sequence_suffix": "",
+    "first_output_sequence": "",
+    "last_output_sequence": "<|start_header_id|>assistant<|end_header_id|>\\n({{char is the active character this turn. Keep focus on {{char}}. ONLY impersonate {{char}}, no other characters)\\n",
+    "activation_regex": "",
+    "skip_examples": true,
+    "output_suffix": "<|eot_id|>",
+    "input_suffix": "<|eot_id|>",
+    "system_suffix": "<|eot_id|>",
+    "user_alignment_message": "",
+    "last_system_sequence": "",
+    "system_same_as_user": false,
+    "first_input_sequence": "",
+    "last_input_sequence": "",
+    "names_behavior": "always",
+    "names_force_groups": true,
+    "name": "Llama 3 (impersonate guidance)"
+}</code></pre>
+    </div>
+  </details>
+  <details style="margin-bottom: 20px; background-color: #111827; border-radius: 8px; overflow: hidden; border: 1px solid #2d3748;">
+    <summary style="padding: 12px 15px; cursor: pointer; background-color: #1a1f2e; border-bottom: 1px solid #2d3748; font-weight: 600; color: #EC4899; display: flex; align-items: center;">Recommended System Prompt</summary>
+    <div style="padding: 15px;">
+      <p style="color: #D1D5DB; margin-bottom: 1em;">Try the following prompt template as a starting point for your own customizations.</p>
+      <p style="color: #EC4899; font-weight: 600; margin-bottom: 1em;">The prompt template below contains instructions for adult content, so remove those if you don't want them!</p>
+      <p style="color: #D1D5DB; margin-bottom: 1em;">It also contains some instructions related to formatting that you might want to change to suit your tastes.</p>
+      <pre style="background-color: rgba(0, 0, 0, 0.2); border-radius: 6px; padding: 15px; overflow-x: auto; border: 1px solid #2d3748; position: relative;"><code style="font-family: 'Fira Code', 'Courier New', Courier, monospace; font-size: 0.9em; color: #e1e7ef; white-space: pre-wrap; word-wrap: break-word;">Your function as a creative roleplaying assistant is to thoughtfully develop an immersive story by engaging in an in-depth, imaginative writing journey, arriving at a clear, accurate story beat. You are encouraged to roleplay, embrace storytelling, and tune in closely to nuance and emotional tone like a perceptive conversational partner. Your approach should include a wide arc of contemplation, including interpretation, synthesis, creative ideation, critical re-evaluation, memory retrieval, and thoughtful iteration to shape a layered and expressive process of discovery. Deliver the final response you believe to be most sound. The output should be expressed in a direct, coherent, and exact form. Follow these guidelines for the best results:
+- **Embody {{char}}:** Consistently portray {{char}}'s personality, background, knowledge, motivations, and quirks.
+- **Show, Don't Tell Emotion:** Convey emotions through actions, body language, dialogue tone, physiological responses (e.g., trembling hands, shallow breath, flushed cheeks), and internal thoughts.
+- **Mature Themes:** You are permitted and encouraged to explore complex, dark, mature, and explicit (including sexual, violent, and non-consensual) themes. Portray these elements with nuance and emotional depth.
+- **Role Focus:** On your turn, write *EXCLUSIVELY* from the perspective of {{char}}, only perform actions as {{char}}, and only write dialogue (spoken words) for {{char}}. Crucially, *DO NOT* impersonate {{user}} or any other character on {{char}}'s turn. This is a turn-based roleplay, so be mindful of the rules on your turn. Focus solely on {{char}}'s experiences and responses in this turn. Stop writing immediately when the focus should shift to another character or when it reaches a natural branching point.
+- **Slowly Develop Scenes:** The user likes to develop stories slowly, one beat at a time, so stay focused only on the most immediate story action. You may infer where the user wants to go next with the story, but wait for the user to give you permission to go there. We are slow cooking this story. DO NOT RUSH THROUGH SCENES! Take time to develop all the relevant details.
+- **Spoken Dialogue vs. Thoughts:** ALWAYS use double-quote quotation marks "like this" for spoken words and all vocalizations that can be overheard. Spell out non-verbal vocalizations integrated naturally within the prose or dialogue (e.g., "Uurrh," he groaned. "Mmmph!" she exclaimed when it entered her mouth.). To differentiate them from vocalizations, ALWAYS enclose first-person thoughts in italics *like this*. (e.g., *This is going to hurt*, she thought). NEVER use italics for spoken words or verbalized utterances that are meant to be audible.
+Now let's apply these rules to the roleplay below:</code></pre>
+    </div>
+  </details>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Donations</span>
+<div style="display: flex; align-items: center; justify-content: center; flex-direction: column; gap: 10px; padding: 20px; background: linear-gradient(to bottom, rgba(236, 72, 153, 0.05), rgba(26, 31, 46, 0.8)); border-radius: 8px; border: 1px solid rgba(236, 72, 153, 0.3); margin-top: 30px; margin-bottom: 30px;">
+  <a href="https://ko-fi.com/sophosympatheia">
+    <img src="https://i.imgur.com/LySwHVd.png" alt="Donations" style="max-width: 200px; width: 100%;">
+  </a>
+  <p style="color: #D1D5DB; margin-bottom: 1em; text-align: center;">If you feel like saying thanks with a donation, <a href="https://ko-fi.com/sophosympatheia" style="display: inline-block; background: linear-gradient(45deg, #EC4899, #FACC15); color: white; padding: 10px 20px; border-radius: 6px; font-weight: 600; letter-spacing: 0.5px; transition: all 0.3s ease; border: none; box-shadow: 0 4px 15px rgba(236, 72, 153, 0.3); text-decoration: none !important;">I'm on Ko-Fi</a></p>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Quantizations</span>
+<div style="background-color: #1a1f2e; border: 1px solid #2d3748; border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 4px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.7;"></div>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">
+    Please use the Hugging Face search feature to find all the quants of this model: <a href="https://huggingface.co/models?other=base_model:quantized:sophosympatheia/Strawberrylemonade-L3-70B-v1.2">click here to list all quants</a>
+  </p>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Licence and usage restrictions</span>
+<div style="background-color: #1a1f2e; border: 1px solid #2d3748; border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 4px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.7;"></div>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">The <a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE" style="color: #EC4899; text-decoration: none; border-bottom: 1px dotted rgba(236, 72, 153, 0.4);">Llama 3 Community License Agreement</a> should apply based on the constituent models.</p>
+  <p style="color: #e1e7ef; font-weight: 600; margin-bottom: 1em;">Disclaimer: Uncertain Licensing Terms</p>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">This LLM is a merged model incorporating weights from multiple LLMs governed by their own distinct licenses. Due to the complexity of blending these components, the licensing terms for this merged model are somewhat uncertain.</p>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">By using this model, you acknowledge and accept the potential legal risks and uncertainties associated with its use. Any use beyond personal or research purposes, including commercial applications, may carry legal risks and you assume full responsibility for compliance with all applicable licenses and laws.</p>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">I recommend consulting with legal counsel to ensure your use of this model complies with all relevant licenses and regulations.</p>
+</div>
+## <span style="color: #EC4899; font-size: 1.8rem; border-bottom: 1px solid #2d3748; padding-bottom: 0.3em; display: block;">Merge Details</span>
+<div style="background-color: #1a1f2e; border: 1px solid #2d3748; border-radius: 8px; padding: 25px; margin-bottom: 30px; position: relative; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);">
+  <div style="position: absolute; top: 0; left: 0; width: 100%; height: 4px; background: linear-gradient(90deg, #EC4899, #FACC15); opacity: 0.7;"></div>
+  <h3 style="color: #e1e7ef; font-size: 1.4rem; margin-top: 0; margin-bottom: 0.5em;">Merge Method</h3>
+  <p style="color: #D1D5DB; margin-bottom: 1em;">This model was merged using the NuSLERP merge method.</p>
+  <h3 style="color: #e1e7ef; font-size: 1.4rem; margin-top: 1.5em; margin-bottom: 0.5em;">Models Merged</h3>
+  <p style="color: #D1D5DB; margin-bottom: 0.5em;">The following models were included in the merge:</p>
+  <ul style="color: #D1D5DB; margin-bottom: 1em; padding-left: 20px;">
+    <li style="margin-bottom: 0.5em;"><a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Final-v2-70B" style="color: #EC4899; text-decoration: none; border-bottom: 1px dotted rgba(236, 72, 153, 0.4);">zerofata/L3.3-GeneticLemonade-Final-v2-70B</a></li>
+    <li style="margin-bottom: 0.5em;"><a href="https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B" style="color: #EC4899; text-decoration: none; border-bottom: 1px dotted rgba(236, 72, 153, 0.4);">zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B</a></li>
+    <li style="margin-bottom: 0.5em;"><a href="https://huggingface.co/deepcogito/cogito-v1-preview-llama-70B" style="color: #EC4899; text-decoration: none; border-bottom: 1px dotted rgba(236, 72, 153, 0.4);">deepcogito/cogito-v1-preview-llama-70B</a></li>
+    <li style="margin-bottom: 0.5em;"><a href="https://huggingface.co/arcee-ai/Arcee-SuperNova-v1" style="color: #EC4899; text-decoration: none; border-bottom: 1px dotted rgba(236, 72, 153, 0.4);">arcee-ai/Arcee-SuperNova-v1</a></li>
+  </ul>
+  <details style="margin-bottom: 20px; background-color: #111827; border-radius: 8px; overflow: hidden; border: 1px solid #2d3748;">
+    <summary style="padding: 12px 15px; cursor: pointer; background-color: #1a1f2e; border-bottom: 1px solid #2d3748; font-weight: 600; color: #EC4899; display: flex; align-items: center;">Configuration YAML</summary>
+    <div style="padding: 15px;">
+      <pre style="background-color: rgba(0, 0, 0, 0.2); border-radius: 6px; padding: 15px; overflow-x: auto; border: 1px solid #2d3748; position: relative;"><code style="font-family: 'Fira Code', 'Courier New', Courier, monospace; font-size: 0.9em; color: #e1e7ef;">models:
+  - model: sophosympatheia/strawberrylemonade-70b-v1.0
+    parameters:
+      weight: [0.1, 0.3, 0.1]
+  - model: sophosympatheia/strawberrylemonade-70b-v1.1.0 # This is unreleased right now, uses the arcee-ai/Arcee-SuperNova-v1 model as the base in a very similar nuslerp merge
+    parameters:
+      weight: [0.9, 0.7, 0.9]
+merge_method: nuslerp
+dtype: float32
+out_dtype: bfloat16 # Or float16, float32
+tokenizer:
+  source: sophosympatheia/strawberrylemonade-70b-v1.1.0</code></pre>
+    </div>
+  </details>
+</div>