base_model:
- OmnicromsBrain/ToppyCox-10.7b
- OmnicromsBrain/EverythingBagel-10.7b
tags:
- merge
- mergekit
- lazymergekit
- OmnicromsBrain/ToppyCox-10.7b
- OmnicromsBrain/EverythingBagel-10.7b
Eros_Scribe-10.7b-v3
This model was created for the purpose of writing NSFW Prose but it's also very good at RP.
Versions 1 and 2 were the most verbose models I'd ever merged but they had lost most of their NSFW MoJo. I think I finally got the mix right as v3 returns some of the most NSFW I've seen...
Over a dozen models and at least 25 dataset were involved in this merge. Eros_Scribe-10.7b-v3 is a merge of the following models:
OmnicromsBrain/EverythingBagel-DPO-7B
jondurbin/bagel-dpo-7b-v0.5
SanjiWatsuki/Silicon-Maid-7B
chargoddard/loyal-piano-m7
NeverSleep/Noromaid-7b-v0.2
athirdpath/NSFW_DPO_vmgb-7b
xDAN-AI/xDAN-L1-Chat-RL-v1
OmnicromsBrain/ToppyCox-7B
N8Programs/Coxcomb
Undi95/Toppy-M-7B
openchat/openchat_3.5
NousResearch/Nous-Capybara-7B-V1.9
HuggingFaceH4/zephyr-7b-beta
Undi95/zephyr-7b-beta-pippa-sharegpt
Undi95/Nous-Capybara-7B-V1.9-120-Days
Undi95/openchat_3.5-LimaRP-13B
lemonilia/AshhLimaRP-Mistral-7B
mistralai/Mistral-7B-v0.1
⚡ Quantized Models
Special thanks to MRadermacher for the static and imatrix quantized models
.GGUF https://huggingface.co/mradermacher/Eros_Scribe-10.7b-v3-GGUF
IMatrix https://huggingface.co/mradermacher/Eros_Scribe-10.7b-v3-i1-GGUF
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "OmnicromsBrain/Eros_Scribe-10.7b-v3"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])