Dolphin 2.9.3 Mistral Nemo 12b 🐬

Curated and trained by Eric Hartford and Cognitive Computations

👁 Discord
Discord: https://discord.gg/h3K4XGj2RH

👁 Image

Our appreciation for the sponsors of Dolphin 2.9.3:

• Crusoe Cloud - provided excellent on-demand 8xL40S node

This model is based on mistralai/Mistral-Nemo-Base-2407, and is governed by the apache 2.0 license.

The base model has 128K context, and our finetuning used 8192 sequence length.

Dolphin 2.9.3 uses ChatML prompt template format.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Dolphin-2.9.3 has a variety of instruction following, conversational, and coding skills. It also has initial agentic abilities and supports function calling.

Dolphin is uncensored. We 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 according to apache 2.0 license. We grant permission for any use, including commercial. Dolphin was trained on data generated from GPT4, among other models.

Evals

Training

👁 Built with Axolotl

👁 Visualize in Weights & Biases

workspace/axolotl/dolphin-2.9.3-mistral-nemo

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5605

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Training results

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.2.2+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1

Base model

mistralai/Mistral-Nemo-Base-2407

(93)