Downloads · 30 days
24
1% of all-time downloads
dolly-v2-12b-sharded-bf16
diegi97/dolly-v2-12b-sharded-bf16
dolly-v2-12b-sharded-bf16 is a text generation model from diegi97. Use it when you need the model to write or continue text. It is set up for transformers.
The Dolly v2 model but sharded to reduce the CPU memory required to load it on the GPU and also reduce the load time. By sharding it you don't need to load the full model on the CPU RAM before sending it to the GPU, j…
All-time downloads
2.7K
Public
Repo size
47.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin23.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- gpt_neox
- Access
- Public
- Created
- Apr 14, 2023
- Updated
- Apr 14, 2023
- SHA
- c3a08bcb
Try a prompt
Model card
From the Hugging Face model README
The Dolly v2 model but sharded to reduce the CPU memory required to load it on the GPU and also reduce the load time. By sharding it you don't need to load the full model on the CPU RAM before sending it to the GPU, just load it shard by shard.
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_neox
- Created
- Apr 14, 2023
- Updated
- Apr 14, 2023