Edit model card

A failed checkpoint of Euryale 1.5, which I have named Lila.

This includes Godzilla2, one of my most favourite 70B L2 models, the model is then trained afterwards.

Just like Solus, She feels pretty smart, and is verbose in her writing. Go ahead and 'plap plap' or 'ah ah mistress'.

I like her writing style, it felt different. Well, I think?

She does feel like a decent improvement over 1.3 and 1.4, but not enough for me to call it Euryale 1.5.

Kinda reluctant in darker NSFW scenarios sometimes like my ex, but all it takes is a little bit of 'convincing' and she'll do it.

Prompt Template: Vicuna 1.1 / Alpaca | Both Works. I tested.

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

or

User: <Prompt>

Assistant:

Enjoy.

Downloads last month
1,081
Safetensors
Model size
69B params
Tensor type
FP16
·
Inference API
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.

Collection including Sao10K/Lila-70B-L2