Downloads · 30 days
29
28% of all-time downloads
EXAONE-3.5-32B-Instruct-Llamafied
datalama/EXAONE-3.5-32B-Instruct-Llamafied
EXAONE-3.5-32B-Instruct-Llamafied is a text generation model from datalama. 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.
- RoPE Scaling Parameter: Added to support longer contextlength. - Memory Optimization: For the 2.4B model, tiewordembeddings is set to True for improved memory efficiency.
All-time downloads
105
Public
Parameters
32B
64 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors64 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Dec 9, 2024
- Updated
- Dec 10, 2024
- SHA
- 79daec9c
Try a prompt
Model card
From the Hugging Face model README
Updates in EXAONE-3.5
Key Changes
- RoPE Scaling Parameter: Added to support longer
context_length. - Memory Optimization: For the 2.4B model,
tie_word_embeddingsis set toTruefor improved memory efficiency.
⚠️ Using the original Llamafy script as-is may lead to performance degradation.
To address this, I have updated the script and uploaded the Llamafied version of the model.
Special Thanks
-
@maywell
For updating the code and uploading the model. -
LG AI Research
For releasing the original model.
Check out the original release here.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Languages
- en, ko
- Created
- Dec 9, 2024
- Updated
- Dec 10, 2024