| | --- |
| | base_model: |
| | - Sao10K/L3.1-70B-Hanami-x1 |
| | - EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 |
| | - LatitudeGames/Wayfarer-Large-70B-Llama-3.3 |
| | - crestf411/L3.1-nemotron-sunfall-v0.7.0 |
| | - tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3 |
| | - SicariusSicariiStuff/Negative_LLAMA_70B |
| | - nbeerbower/llama3.1-kartoffeldes-70B |
| | - deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
| | library_name: transformers |
| | tags: |
| | - mergekit |
| | - merge |
| | --- |
| | # Genetic Lemonade Unleashed |
| |
|
| |  |
| |
|
| | Inspired to learn how to merge by the Nevoria series from [SteelSkull](https://huggingface.co/Steelskull). |
| |
|
| | This model is the result of a few dozen different attempts of learning how to merge. |
| |
|
| | ## Model Comparison |
| |
|
| | Designed for RP and creative writing, all three models are focused around striking a balance between writing style, creativity and intelligence. The basic differences between the models are below. |
| |
|
| | | Version | Strength | Weakness | |
| | |---------|----------------|----| |
| | | **Unleashed** | Well balanced | Somewhat censored | |
| | | Final | Fully uncensored | Least intelligent | |
| | | Sunset | Well balanced, most intelligent | GPTisms / weakest writing style | |
| |
|
| | ## SillyTavern Settings |
| |
|
| | [Llam@ception](https://huggingface.co/Konnect1221/The-Inception-Presets-Methception-LLamaception-Qwenception/tree/main/Llam%40ception) recommended for sane defaults if unsure, import them to SillyTavern and they're plug n play. |
| |
|
| | ### Sampler Settings |
| | - Temp: 0.9-1.0 |
| | - MinP: 0.03-0.05 |
| | - Dry: 0.8, 1.75, 4 |
| |
|
| | Temperature last, neutralize other samplers. This model natively strikes a balance of creativity & intelligence. |
| |
|
| | ### Instruct |
| |
|
| | Llama-3-Instruct-Names but you will need to uncheck "System same as user". |
| |
|
| | ## Quants |
| |
|
| | ### GGUF |
| | - [Static quants by mradermacher](https://huggingface.co/mradermacher/L3.3-GeneticLemonade-Unleashed-70B-GGUF) |
| | - [Imatrix quants by mradermacher](https://huggingface.co/mradermacher/L3.3-GeneticLemonade-Unleashed-70B-i1-GGUF) |
| |
|
| | ### EXL2 |
| | - [4.5bpw](https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-70B-4.5bpw-h6-exl2) |
| | - [6bpw](https://huggingface.co/zerofata/L3.3-GeneticLemonade-Unleashed-70B-6bpw-h8-exl2) |
| |
|
| | ## Merge Details |
| | ### Merge Method |
| |
|
| | This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method. |
| |
|
| | ### merge_v6_base_E |
| | ```yaml |
| | models: |
| | - model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
| | - model: nbeerbower/llama3.1-kartoffeldes-70B |
| | - model: tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3 |
| | - model: SicariusSicariiStuff/Negative_LLAMA_70B |
| | select_topk: .15 |
| | merge_method: sce |
| | base_model: meta-llama/Llama-3.3-70B-Instruct |
| | out_dtype: bfloat16 |
| | dype: float32 |
| | tokenizer: |
| | source: base |
| | ``` |
| | |
| | ### Genetic Lemonade Unleashed |
| | |
| | ```yaml |
| | models: |
| | - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 |
| | - model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3 |
| | - model: crestf411/L3.1-nemotron-sunfall-v0.7.0 |
| | - model: Sao10K/L3.1-70B-Hanami-x1 |
| | merge_method: sce |
| | base_model: ./merge_v6_base_E |
| | select_topk: 0.15 |
| | out_dtype: bfloat16 |
| | dype: float32 |
| | tokenizer: |
| | source: union |
| | ``` |
