dphn / dolphin-2.2.1-mistral-7b

huggingface.co
Total runs: 530
24-hour runs: 27
7-day runs: -97
30-day runs: -71
Model's Last Updated: May 20 2024
text-generation

Introduction of dolphin-2.2.1-mistral-7b

Model Details of dolphin-2.2.1-mistral-7b

dolphin-2.2.1-mistral-7b

Dolphin 2.2.1 🐬 https://erichartford.com/dolphin

Discord Discord: https://discord.gg/cognitivecomputations

This is a checkpoint release, to fix overfit training. ie, it was responding with CoT even when I didn't request it, and also it was too compliant even when the request made no sense. This one should be better.

Dolphin-2.2.1-mistral-7b's training was sponsored by a16z .

This model is based on mistralAI , with apache-2.0 license, so it is suitable for commercial or non-commercial use.

New in 2.2 is conversation and empathy. With an infusion of curated Samantha DNA, Dolphin can now give you personal advice and will care about your feelings, and with extra training in long multi-turn conversation.

This model 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 to 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.

Dataset

This dataset is Dolphin, an open-source implementation of Microsoft's Orca

I modified the dataset for uncensoring, deduping, cleaning, and quality.

I added Jon Durbin's excellent Airoboros dataset to increase creativity.

I added a curated subset of WizardLM and Samantha to give it multiturn conversation and empathy.

Training

It took 48 hours to train 4 epochs on 4x A100s.

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
Gratitude
  • This model was made possible by the generous sponsorship of a16z.
  • Thank you to Microsoft for authoring the Orca paper and inspiring this work.
  • Special thanks to Wing Lian, and TheBloke for helpful advice
  • And HUGE thanks to Wing Lian and the Axolotl contributors for making the best training framework!
  • Built with Axolotl
  • Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
Example Output

image/png

image/png

Buy me a coffee

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 6e-06
  • train_batch_size: 5
  • eval_batch_size: 5
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 80
  • total_eval_batch_size: 20
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 4
Framework versions
  • Transformers 4.34.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.0

Runs of dphn dolphin-2.2.1-mistral-7b on huggingface.co

530
Total runs
27
24-hour runs
-14
3-day runs
-97
7-day runs
-71
30-day runs

More Information About dolphin-2.2.1-mistral-7b huggingface.co Model

More dolphin-2.2.1-mistral-7b license Visit here:

https://choosealicense.com/licenses/apache-2.0

dolphin-2.2.1-mistral-7b huggingface.co

dolphin-2.2.1-mistral-7b huggingface.co is an AI model on huggingface.co that provides dolphin-2.2.1-mistral-7b's model effect (), which can be used instantly with this dphn dolphin-2.2.1-mistral-7b model. huggingface.co supports a free trial of the dolphin-2.2.1-mistral-7b model, and also provides paid use of the dolphin-2.2.1-mistral-7b. Support call dolphin-2.2.1-mistral-7b model through api, including Node.js, Python, http.

dolphin-2.2.1-mistral-7b huggingface.co Url

https://huggingface.co/dphn/dolphin-2.2.1-mistral-7b

dphn dolphin-2.2.1-mistral-7b online free

dolphin-2.2.1-mistral-7b huggingface.co is an online trial and call api platform, which integrates dolphin-2.2.1-mistral-7b's modeling effects, including api services, and provides a free online trial of dolphin-2.2.1-mistral-7b, you can try dolphin-2.2.1-mistral-7b online for free by clicking the link below.

dphn dolphin-2.2.1-mistral-7b online free url in huggingface.co:

https://huggingface.co/dphn/dolphin-2.2.1-mistral-7b

dolphin-2.2.1-mistral-7b install

dolphin-2.2.1-mistral-7b is an open source model from GitHub that offers a free installation service, and any user can find dolphin-2.2.1-mistral-7b on GitHub to install. At the same time, huggingface.co provides the effect of dolphin-2.2.1-mistral-7b install, users can directly use dolphin-2.2.1-mistral-7b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

dolphin-2.2.1-mistral-7b install url in huggingface.co:

https://huggingface.co/dphn/dolphin-2.2.1-mistral-7b

Url of dolphin-2.2.1-mistral-7b

dolphin-2.2.1-mistral-7b huggingface.co Url

Provider of dolphin-2.2.1-mistral-7b huggingface.co

dphn
ORGANIZATIONS

Other API from dphn

huggingface.co

Total runs: 225
Run Growth: 208
Growth Rate: 92.44%
Updated:December 08 2025
huggingface.co

Total runs: 127
Run Growth: 0
Growth Rate: 0.00%
Updated:October 14 2025
huggingface.co

Total runs: 29
Run Growth: 12
Growth Rate: 41.38%
Updated:November 07 2023
huggingface.co

Total runs: 18
Run Growth: 10
Growth Rate: 55.56%
Updated:April 07 2024