Hugging Face's logo

wasertech
/
assistant-llama2-7b-chat

Text Generation
Transformers
PyTorch
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
assistant-llama2-7b-chat / README.md
wasertech's picture
wasertech
Update README.md
da406a4
preview code
|
raw
history blame
1.84 kB
metadata
license: llama2
base_model: Photolens/llama-2-7b-langchain-chat
tags:
  - generated_from_trainer
model-index:
  - name: assistant-llama2-7b-chat
    results: []
datasets:
  - wasertech/OneOS

assistant-llama2-7b-chat

This model is a fine-tuned version of Photolens/llama-2-7b-langchain-chat on the OneOS dataset.

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: 1.41e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Model is able to mostly answer to complexe queries given its output is parsed propely (accounting for hallucinations).

For more information look at the Prompt Example Section

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3

Training Report

https://wandb.ai/wasertech/huggingface/reports/Llama2-langchain-chat-fine-tune--Vmlldzo1NTQ2OTAy

Prompt Example

The above link leads to a conversation log between Assistant using this model and me.

https://gist.github.com/wasertech/342cd167ba78060336b3328e9eea0eca