|
|
--- |
|
|
base_model: |
|
|
- allura-org/GLM4-9B-Neon-v2 |
|
|
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/ckSuw.webp"> **For RP & story gen,<br/>GLM-4-9B played a safe card and wins the secret lottery. It proves hexagon is powerful without blade, that goodness lies in fewer mistakes.<br/>The 0414 version dropped hot in fine-tuners' hands while the air is still cold.<br/>People see a silent goat fit in human skin,<br/>graduated from Tsinghua and going to MIT...<br/><br/>Actually an abliteration is already enough,<br/>though [huihui-ai/GLM-4-9B-0414-abliterated](https://huggingface.co/huihui-ai/GLM-4-9B-0414-abliterated) hit mergekit with download error. Anyway [THUDM/LongReward-glm4-9b-DPO](https://huggingface.co/THUDM/LongReward-glm4-9b-DPO) should lower some censorship,<br/>helping the one [allura-org/GLM4-9B-Neon-v2](https://huggingface.co/allura-org/GLM4-9B-Neon-v2) go shameless.<br/><br/>It seldom jumps out of simulation; refreshing is the key to trance the Hobbit.<br/>Save your effort for seduction,<br/>possess by defining the fact.** | |
|
|
|:---:| |
|
|
<small>*"Young transformers start from playing Rubik's cubes."*</small> |
|
|
```yaml |
|
|
models: |
|
|
- model: allura-org/GLM4-9B-Neon-v2 |
|
|
- model: THUDM/LongReward-glm4-9b-DPO |
|
|
parameters: |
|
|
weight: [0.496, 0.166, 0.166, 0.496, 0.496, 0.166, 0.166, 0.496] |
|
|
base_model: allura-org/GLM4-9B-Neon-v2 |
|
|
merge_method: sce |
|
|
parameters: |
|
|
select_topk: 0.06 |
|
|
lambda: 0.66 |
|
|
tokenizer_source: base |
|
|
dtype: float32 |
|
|
out_dtype: bfloat16 |
|
|
``` |
|
|
|
