Sao10K/Venomia-1.1-m7

Venomia: Derived from 'venom', the name suggests a lethal charm, embodying the dangerous beauty of both cats and poisons. It evokes an image of a sleek, enigmatic feline, with a hidden, perilous side.

Now that is out of the way, this model is a qLoRA tune with a 4090 taking roughly 5 hours over 4 epochs, trained from the 7B Mistral base. Took the 3rd Epoch Checkpoint due to 4th Overfitting.

The goal is to create a model that is Toxic, while being capable of RP, and is still capable of general Instruct / Assistant Capabilities.

---

V1.1 Changelogs - Added More RP/Instruct Mixes to Dataset. Cleaned it up a little.

---

General Observations:

• Quite Uncensored even with the most NSFL of topics. All it takes is one swipe if there is any refusal, but so far I rarely had to swipe.
• A bit unhinged at times. Made me laugh a bit.
• Responses are a bit longer than v1. feels nice?
• I may need to swipe once or twice while using it as an Assistant-type model, but it is 7b so it is really rapid, I see no downsides.

---

Trained with Alpaca Format:

### Instruction:
<Prompt>

### Response:

OR

### Instruction:
<Prompt>

### Input:
<Insert Context Here>

### Response:

Meow.

---

Total Dataset Composition: 32K Entries of up to 4096 Token Length Each.

- Roleplay: 10K
- Medical Information: 4K
- Mixed Instruct: 12K
- De-Alignment: 6K

---

Using a subset of Hesperus, and the Euryale 1.3 sauce, refined a bit. I think Ministrations 7B is a bit dumb but eh its a fun attempt. Just an experimental model.