Downloads · 30 days
30
39% of all-time downloads
Orca-2-13b_flat
TeeZee/Orca-2-13b_flat
Orca-2-13b_flat is a text generation model from TeeZee. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Lots of good models use Orca for their merges, however vanilla Orca has vocabulary size of 32003, 3 last tokens are ChatML tokens and a PAD token. This causes errors during a merge with models with standard 32000 voca…
All-time downloads
76
Public
Parameters
13B
52.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors52.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Feb 18, 2024
- Updated
- Feb 19, 2024
- SHA
- 7eb57564
Try a prompt
Model card
From the Hugging Face model README
Lots of good models use Orca for their merges, however vanilla Orca has vocabulary size of 32003, 3 last tokens are ChatML tokens and a PAD token. This causes errors during a merge with models with standard 32000 vocabulary size.
I've removed those tokens from volabulary and resized model embeddings to mach 32000 standard size. So this model is ready to be used as a merge component in mergekit. It may not work on its own with ChatML template anymore.
model.resize_token_embeddings(32000)
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Created
- Feb 18, 2024
- Updated
- Feb 19, 2024