|
--- |
|
base_model: |
|
- Qwen/Qwen2.5-72B-Instruct |
|
tags: |
|
- conversational |
|
- roleplay |
|
- chat |
|
license: other |
|
license_name: qwen |
|
--- |
|
# Qwen 2.5 72b RP Ink |
|
 |
|
A roleplay-focused LoRA finetune of Qwen 2.5 72b Instruct. Methodology and hyperparams inspired by [SorcererLM](https://huggingface.co/rAIfle/SorcererLM-8x22b-bf16) and [Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush). |
|
Yet another model in the Ink series, following in the footsteps of [the 32b one](https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink) and [the Nemo one](https://huggingface.co/allura-org/MN-12b-RP-Ink) |
|
|
|
## Testimonials |
|
> [Compared to the 32b] felt a noticeable increase in coherence |
|
|
|
\- ShotMisser64 |
|
|
|
> Yeah ep2's great!! made me actually wanna write a reply by myself for the first time in a few days |
|
|
|
\- Maw |
|
|
|
> This is the best RP I've ever had |
|
|
|
\- 59smoke |
|
|
|
> this makes me want to get another 3090 to run 72b |
|
|
|
\- dysfunctional |
|
|
|
## Dataset |
|
The worst mix of data you've ever seen. Like, seriously, you do not want to see the things that went into this model. It's bad. |
|
|
|
"this is like washing down an adderall with a bottle of methylated rotgut" - inflatebot |
|
|
|
Update: I have sent the (public datasets in the) data mix publicly already so here's that |
|
<details> |
|
<img src=https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/JtjUoKtbOfBZfSSKojTcj.png> |
|
</details> |
|
|
|
## Quants |
|
[imatrix GGUFs by bartowski](https://huggingface.co/bartowski/Qwen2.5-72b-RP-Ink-GGUF) |
|
|
|
## Recommended Settings |
|
Chat template: ChatML |
|
Recommended samplers (not the be-all-end-all, try some on your own!): |
|
- Temp 0.83 / Top P 0.8 / Top A 0.3 / Rep Pen 1.03 |
|
- Your samplers can go here! :3 |
|
|
|
## Hyperparams |
|
### General |
|
- Epochs = 2 |
|
- LR = 6e-5 |
|
- LR Scheduler = Cosine |
|
- Optimizer = Paged AdamW 8bit |
|
- Effective batch size = 16 |
|
### LoRA |
|
- Rank = 16 |
|
- Alpha = 32 |
|
- Dropout = 0.25 (Inspiration: [Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush)) |
|
|
|
## Credits |
|
Humongous thanks to the people who created and curated the original data |
|
Big thanks to all Allura members, for testing and emotional support ilya /platonic |
|
especially to inflatebot who made the model card's image :3 |
|
Another big thanks to all the members of the ArliAI and BeaverAI Discord servers for testing! All of the people featured in the testimonials are from there :3 |
