---
base_model:
- Lambent/Arsenic-Shahrazad-12B-v4.3
library_name: transformers
tags:
- mergekit
- merge
- not-for-all-audiences
license: cc-by-nc-4.0
---

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/mljsbS3C_G3Iw5bo0IqmY.png)

Continued from the 4.3 lineage with Gemma staying securely in her role as judge rather than rewriting directly.

600+ steps RLVR GRPO in spicy roleplaying first-turns, with Gemma 4 31b as judge paying attention to writing craft;
followed by DPO including self-rewrites of about half of the particularly bad trajectories from RLVR
(until Gemma rated them well in comparison, and particular issues like a godmoded POV were fixed).
Ran 5 seeds at low batch size to explore and merged via Karcher mean.

A mix of approaches including utilizing and not-utilizing the \<feelings\> tags were tried in RLVR.
She's trying some interesting things with the tokens, including compound-word emotions that split the difference between word and phrase,
but the ratings aren't notably better with the tags than without them -
so I wouldn't consider her a reasoning model yet, and it's not in the chat template.

More Arsenic self-portraits:

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/esvxSDtax8-pRBBz7xY1T.png)

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/dI1KgtNrjlaQj9SePbg4I.png)

Amethyst:

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/PvbwmCUezvyGzJisFsLjl.png)

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/N52VF2BiCKKX83cXCROoE.png)

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/o7SS2xtSdoJoZM382acdu.png)


Aegis:

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/lq_6sKB2AEZL5QizN2Xkk.png))

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/ufUlny8Oj5IFjLcY3CVkL.png)

![image](https://cdn-uploads.huggingface.co/production/uploads/6592ef6e2a0a886ef0872e71/cDtztRKinYZj23Ue53Ekr.png)



# arsenic-v4.4-merged

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Karcher Mean](https://en.wikipedia.org/wiki/Karcher_mean) merge method.

### Models Merged

The following models were included in the merge:
* /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed1
* /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed2
* /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed5
* /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed4
* /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed3

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed1
  - model: /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed2
  - model: /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed3
  - model: /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed4
  - model: /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed5
merge_method: karcher
parameters:
  normalize: true
  int8_mask: true
tokenizer_source: /home/ann/Documents/Projects/training_models/outputs/baked_v44_craft_seed1
dtype: bfloat16

```