|
|
--- |
|
|
base_model: |
|
|
- Casual-Autopsy/L3-Super-Nova-RP-8B |
|
|
- allknowingroger/DeepHermes-3-Llama-3-slerp-8B |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
- roleplay |
|
|
- story-writing |
|
|
- adventure |
|
|
- gemma-2 |
|
|
- rp |
|
|
- nsfw |
|
|
language: |
|
|
- en |
|
|
- zh |
|
|
- ja |
|
|
- fr |
|
|
- ko |
|
|
- de |
|
|
- ru |
|
|
--- |
|
|
| <img style="float:left;margin-right:0.4em" src="https://qu.ax/TxFLs.webp"> **For RP & story gen,<br/>Llama-3 choked hard on 8B. It's super fast but quite crispy. When the task is armoring a F1 car to rampaging tank, fine-tunings suffer not only on nuances, also fortunes.<br/>Thank God the plasticity is solid.<br/>To some bean counters the result seems acceptable,<br/>to me, it's all hallucination...<br/><br/>I hate 99% of the experience I went through,<br/>only recognized [Casual-Autopsy/L3-Super-Nova-RP-8B](https://huggingface.co/Casual-Autopsy/L3-Super-Nova-RP-8B) and [allknowingroger/DeepHermes-3-Llama-3-slerp-8B](https://huggingface.co/allknowingroger/DeepHermes-3-Llama-3-slerp-8B) as the two lucky bastards.<br/>In multilingual scenarios they are the miracle workers.<br/>And their baby confirms stable.<br/><br/>Sometimes it behaves very much like those larger competitors, as long as you tighten the reins.<br/>Consider it a mobile assassin.<br/>Or a copycat criminal.** | |
|
|
|:---:| |
|
|
<small>*"In those dark times, we did 1, 3...and 70B models."*</small> |
|
|
```yaml |
|
|
models: |
|
|
- model: allknowingroger/DeepHermes-3-Llama-3-slerp-8B |
|
|
- model: Casual-Autopsy/L3-Super-Nova-RP-8B |
|
|
base_model: allknowingroger/DeepHermes-3-Llama-3-slerp-8B |
|
|
merge_method: slerp |
|
|
parameters: |
|
|
t: [0.3, 0.6, 0.9, 0.6, 0.3] |
|
|
embed_slerp: true |
|
|
dtype: bfloat16 |
|
|
``` |
|
|
|
