Edit model card

Assistant Dolphin 2.2.1 Mistral 7B (1 epoch) AWQ

This model is a quantized version of Assistant Dolphin 2.2.1 Mistral 7B (1 epoch) using AWQ.

Model description

Assistant Dolphin 2.2.1 Mistral 7B is a fine-tuned version of the cognitivecomputations/dolphin-2.2.1-mistral-7b model on the OneOS dataset for an epoch.

Intended uses & limitations

This model is intended to be used in natural language processing systems to improve text understanding and generation. Specific limitations will depend on the training and evaluation data.

Training and evaluation data

The model was trained on the OneOS dataset.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1.41e-05
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Framework versions

  • AutoAWQ 0.1.8
  • PEFT 0.7.2.dev0
  • Transformers 4.37.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.2.dev0
  • Tokenizers 0.15.0

Example usage

Using transformers and AutoAWQ:

pip install -U transformers autoawq
# Use a pipeline as a high-level helper
from transformers import pipeline

messages = [
    {"role": "system", "content": "You are an helpful Assistant."},
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="wasertech/assistant-dolphin-2.2.1-mistral-7b-e1-awq", max_length=8096)
pipe(messages)

Outputs

[
  {
    'generated_text': [
      {'role': 'system', 'content': 'You are an helpful Assistant.'},
      {'role': 'user', 'content': 'Who are you?'},
      {'role': 'assistant', 'content': '<|im_start|> Assistant\nI am an artificial intelligence language model. My purpose is to provide information, advice, and assistance to users. I can perform many tasks, such as answering questions, explaining concepts, generating reports, or summarizing data. I am a tool that can be used to help you learn new things, make decisions, and achieve your goals. I do not have feelings, opinions, or personal experiences; I am simply a helpful resource to share knowledge and support users. What can I do for you?'}
    ]
  }
]

Parsed Assistant answer:

I am an artificial intelligence language model. My purpose is to provide information, advice, and assistance to users. I can perform many tasks, such as answering questions, explaining concepts, generating reports, or summarizing data. I am a tool that can be used to help you learn new things, make decisions, and achieve your goals. I do not have feelings, opinions, or personal experiences; I am simply a helpful resource to share knowledge and support users. What can I do for you?

Downloads last month
29
Safetensors
Model size
1.2B params
Tensor type
I32
·
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train wasertech/assistant-dolphin-2.2.1-mistral-7b-e1-awq

Collection including wasertech/assistant-dolphin-2.2.1-mistral-7b-e1-awq