Edit model card

Dolphin 2.9.1 Phi-3 Kensho 4.5b (abliterated) 🐬 GGUF

⚠️ This model does not work well, I have wasted my time quantizing it and you will waste your time downloading it.

This model uses ChatML Phi 3 (ignore below) prompt template format, and also needs <br> as one of its end codes for some reason. example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Downloads last month
108
GGUF
Model size
6.54B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for thatlukedev/Dolphin-2.9.1-Phi-3-Kensho-4.5B-abliterated-v3-gguf

Datasets used to train thatlukedev/Dolphin-2.9.1-Phi-3-Kensho-4.5B-abliterated-v3-gguf