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
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
/
tokenizer_config.json
ichitaka
Upload tokenizer
13e27e0
about 1 year ago
raw
Copy download link
history
blame
No virus
180 Bytes
{
"add_prefix_space"
:
false
,
"clean_up_tokenization_spaces"
:
true
,
"eos_token"
:
"<|endoftext|>"
,
"model_max_length"
:
2048
,
"tokenizer_class"
:
"PreTrainedTokenizerFast"
}