Downloads · 30 days
0
mlc-chat-dolphin-2.2.1-mistral-7b-q4f32_1
hrishioa/mlc-chat-dolphin-2.2.1-mistral-7b-q4f32_1
mlc-chat-dolphin-2.2.1-mistral-7b-q4f32_1 is a machine learning model from hrishioa. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
- Original model: Dolphin 2.1 🐬 - creator: Eric Hartford: https://erichartford.com/dolphin - compiled by: Hrishi Olickel: say hi on Twitter!
Access
Public
Updated Nov 9, 2023
Repo size
4.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin4.5 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Nov 6, 2023
- Updated
- Nov 9, 2023
- SHA
- bb4af0c1
Base models
Model card
From the Hugging Face model README
Dolphin 2.2.1 (Finetune of Mistral 7B) compiled for WebGPU - q4f32_1
- Original model: Dolphin 2.1 🐬
- creator: Eric Hartford: https://erichartford.com/dolphin
- compiled by: Hrishi Olickel: say hi on Twitter!
Demo
You can access this model over the browser here.
Description
This is a quantized version of Dolphin 2.1 🐬, one of the best finetunes of Mistral-7b out there, ready to be used for on-browser inference over WebGPU.
Compiled with mlc-llm.
Very helpful direction provided by felladrin!
Prompt template: Dolphin
Prompt format: This model (and all my future releases) use ChatML prompt format.
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Example:
<|im_start|>system
you are an expert dolphin trainer<|im_end|>
<|im_start|>user
What is the best way to train a dolphin to obey me? Please answer step by step.<|im_end|>
<|im_start|>assistant
- License
- apache-2.0
- Languages
- en
- Created
- Nov 6, 2023
- Updated
- Nov 9, 2023