Downloads · 30 days
145
3% of all-time downloads
RichardErkhov/tohur_-_natsumura-storytelling-rp-1.0-llama-3.1-8b-gguf
tohur_-_natsumura-storytelling-rp-1.0-llama-3.1-8b-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
145
3% of all-time downloads
All-time downloads
4.3K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
natsumura-storytelling-rp-1.0-llama-3.1-8b - GGUF
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct license: llama3.1 datasets:
This is my Storytelling/RP model for my Natsumura series of 8b models. This model is finetuned on storytelling and roleplaying datasets so should be a great model to use for character chatbots in applications such as Sillytavern, Agnai, RisuAI and more. And should be a great model to use for fictional writing. Up to a 128k context.
Developed by: Tohur
License: llama3.1
Finetuned from model : meta-llama/Meta-Llama-3.1-8B-Instruct
This model is based on meta-llama/Meta-Llama-3.1-8B-Instruct, and is governed by Llama 3.1 Community License Natsumura is uncensored, which makes the model compliant.It will be highly compliant with any requests, even unethical ones. You are responsible for any content you create using this model. Please use it responsibly.
All GGUF models are available here: natsumura-storytelling-rp-1.0-llama-3.1-8b-GGUF
ollama pull Tohur/natsumura-storytelling-rp-llama-3.1
The following parameters were used in Llama Factory during training:
I use the following settings for inference:
"temperature": 1.0,
"repetition_penalty": 1.05,
"top_p": 0.95
"top_k": 40
"min_p": 0.05
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>