131072 Context
$0.390 / 1M input tokens
$0.390 / 1M output tokens
Demo
API
Model Configuration
Response format
System Prompt
max_tokens
temperature
top_p
min_p
top_k
presence_penalty
frequency_penalty
repetition_penalty
README

Dolphin 2.9.2 Mixtral 8x22b

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

Discord: https://discord.gg/cognitivecomputations

New in 2.9.2 is SystemChat 2.0 - a dataset designed to teach Dolphin to obey the system prompt, even over a long conversation.

My appreciation for the sponsors of Dolphin 2.9.2:

  • Crusoe Cloud - provided excellent on-demand 8xH100 node
  • OnDemand - provided inference sponsorship, enabling creation of SystemChat

This model is based on Dolphin-2.9-Mixtral-8x22b, and is Apache-2.0 licensed.

The base model has 64k context, and fine-tuning was with 16k sequence length.

It took 1 week on 8xH100 provided by Crusoe Cloud

This model was trained FFT on 50% parameters (targeted with Laser Scanner by Fernando Fernandes, David Golchinfar, Lucas Atkins, and Eric Hartford), using ChatML prompt template format.

My appreciation for the sponsors of Dolphin 2.9.2:

  • Crusoe Cloud - provided excellent on-demand 8xH100 node
  • OnDemand - provided inference sponsorship, enabling creation of SystemChat

This model is based on Dolphin-2.9-Mixtral-8x22b, and is Apache-2.0 licensed.

The base model has 64k context, and fine-tuning was with 16k sequence length.

It took 1 week on 8xH100 provided by Crusoe Cloud

This model was trained FFT on 50% parameters (targeted with Laser Scanner by Fernando Fernandes, David Golchinfar, Lucas Atkins, and Eric Hartford), using ChatML prompt template format.

example:

1<|im_start|>system 2You are Dolphin, a helpful AI assistant.<|im_end|> 3<|im_start|>user 4{prompt}<|im_end|> 5<|im_start|>assistant

Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.

Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

Dolphin is licensed Apache 2.0. I grant permission for any use, including commercial, that falls within accordance with Apache-2.0 license. Dolphin was trained on data generated from GPT4, among other models.