Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
LumiOpen
/
Viking-7B
like
29
Text Generation
Transformers
Safetensors
cerebras/SlimPajama-627B
bigcode/starcoderdata
mc4
7 languages
llama
Inference Endpoints
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
New discussion
New pull request
Resources
PR & discussions documentation
Code of Conduct
Hub documentation
All
Discussions
Pull requests
View closed (0)
Custom tokenizer support for llama.cpp?
7
#2 opened 1 day ago by
akx
Example to load fails for GPUs with no bfloat16 support.
1
#1 opened 2 days ago by
RASMUS