Downloads · 30 days
190
1% of all-time downloads
bluemoonrp-30b
reeducator/bluemoonrp-30b
bluemoonrp-30b is a text generation model from reeducator. Use it when you need the model to write or continue text. It is set up for transformers.
Bluemoon roleplay finetune of LLaMA 33B (2 roleplayers only). This release also tests a longer 4k context token size achieved with AliBi.
All-time downloads
30.7K
Public
Repo size
39.9 GB
Likes
24
Public
Repo makeup
Click a slice to open those files.
.bin22.4 GB · 56%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- May 24, 2023
- Updated
- May 25, 2023
- SHA
- 372a1a6a
Try a prompt
Model card
From the Hugging Face model README
General
Bluemoon roleplay finetune of LLaMA 33B (2 roleplayers only). This release also tests a longer 4k context token size achieved with AliBi.
Models
GGML 4-bit for llama.cpp<br/>
- ggml-bluemoonrp-30b-4k-epoch6-q5_0.bin
GPTQ 4-bit CUDA:<br/>
- bluemoonrp-30b-4k-epoch6-4bit-128g.safetensors
Remarks
This model has been trained using the following prompt (Vicuna 1.1 format):
A transcript of a roleplay between two players, LEAD and ASSOCIATE. LEAD sets up a scenario and the characters, from which ASSOCIATE then assumes a character role and continues the story for that role in response to description given by LEAD. The story and characters are developed by exchange of detailed event descriptions and character dialogs, successively given by both LEAD and ASSOCIATE.
LEAD: [role1 message]
ASSOCIATE: [role2 message]</s>
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Languages
- en
- Created
- May 24, 2023
- Updated
- May 25, 2023