The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
7b
271.6K Pulls Updated 7 months ago
Updated 7 months ago
7 months ago
5dc8c5a2be65 · 4.1GB
model
archllama
·
parameters7.24B
·
quantizationQ4_0
4.1GB
system
You are Dolphin, a helpful AI assistant.
41B
params
{"stop":["\u003c|im_start|\u003e","\u003c|im_end|\u003e"]}
59B
template
{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
182B
license
Apache License
Version 2.0, January 2004
11kB
Readme
The Dolphin model by Eric Hartford, based on Mistral version 0.2 released in March 2024. This model is uncensored, available for both commercial and non-commercial use, and excels at coding.
Versions
| Tag | Date | Notes |
|---|---|---|
v2.8 latest |
03/31/2024 | Based on Mistral 0.2 with support for a context window of 32K tokens. |
v2.6 |
12/27/2023 | Fixed a training configuration issue that improved quality, and improvements to the training dataset for empathy. |
v2.2.1 |
10/30/2023 | This is a checkpoint release, to fix overfit training |
v2.2 |
10/29/2023 | Added conversation and empathy data. |
v2.1 |
10/11/2023 | Enhanced with the airoboros dataset. |
v2.0 |
10/2/2023 | Initial release of the model. |