zoyllm-7b-slimorca / README.md
tlphams's picture
Update README.md
34aa2e5
|
raw
history blame
1.12 kB
metadata
license: cc-by-nc-sa-4.0
pipeline_tag: text-generation
language:
  - en
tags:
  - finetuned

Model Card for ZoyLLM-7B-SlimOrca

The ZoyLLM-7B-SlimOrca Large Language Model (LLM) is a LoRA-finetuned generative text model with Mistral-7B-v0.1 is the base model. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.

Model Architecture

ZoyLLM-7B-SlimOrca is a transformer model, with the following architecture choices:

  • Grouped-Query Attention
  • Sliding-Window Attention
  • Byte-fallback BPE tokenizer

Datasets

  • Self-introduction (20 samples)
  • SlimOrca (100k samples random sampled)
  • EverythingLM v3

Template

We finetuned the model using a template similar to the dolphin chat template

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Troubleshooting

  • If you see the following error:
KeyError: 'mistral'
  • Or:
NotImplementedError: Cannot copy out of meta tensor; no data!

Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer.

The Zoy AI Team

Pham Tung Lam, Nguyen Duc Nhan.