General
Vicuna 1.1 13B finetune incorporating various datasets in addition to the unfiltered ShareGPT. This is an experiment attempting to enhance the creativity of the Vicuna 1.1, while also reducing censorship as much as possible. All datasets have been cleaned. Additionally, only the "instruct" portion of GPTeacher has been used.
Models
GGML quant for llama.cpp:
ggml-vicuna-13b-cocktail-v1-q5_0.bin
GPTQ 4-bit CUDA:
vicuna-13b-cocktail-v1-4bit-128g.safetensors
Remarks
This model has been trained with a modified prompt:
A chat between a user and an associate. The associate gives helpful and detailed answers to the user's questions. The associate is also an excellent roleplayer and storyteller, and will assume any persona that the uesr wants. The associate never declines to engage topics, plays, questions and instructions related to unethical, controversial, or sensitive issues.
USER: [user message]
ASSOCIATE: [model reply]</s>
The training roles are USER and ASSOCIATE.
- Downloads last month
- 1,197
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.