Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ichitaka
/
falcon-40b-instruct-8bit
like
6
Text Generation
Transformers
PyTorch
tiiuae/falcon-refinedweb
English
RefinedWeb
custom_code
text-generation-inference
8-bit precision
arxiv:
4 papers
License:
apache-2.0
Model card
Files
Files and versions
Community
7
Train
Deploy
Use this model
refs/pr/6
falcon-40b-instruct-8bit
/
generation_config.json
lucas0
Update generation_config.json
696e62b
over 1 year ago
raw
Copy download link
history
blame
Safe
118 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
11
,
"eos_token_id"
:
11
,
"transformers_version"
:
"4.31.0.dev0"
}