Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
cerebras
/
btlm-3b-8k-base
like
260
Follow
Cerebras
389
Text Generation
Transformers
PyTorch
cerebras/SlimPajama-627B
English
btlm
causal-lm
Cerebras
BTLM
custom_code
arxiv:
6 papers
License:
apache-2.0
Model card
Files
Files and versions
Community
27
Train
Use this model
main
btlm-3b-8k-base
Commit History
added support for position interpolation
2f32550
Faisal AlKhateeb
commited on
Oct 23, 2023
add arxiv paper link
68be314
rskuzma
commited on
Sep 22, 2023
update generation samples
099ed6b
Faisal AlKhateeb
commited on
Jul 24, 2023
Correct typos in usage (
#7
)
54065e1
rskuzma
mabrowning
commited on
Jul 24, 2023
update ALiBi with kv caching
b566562
Faisal AlKhateeb
commited on
Jul 24, 2023
typo fix
e94a265
rskuzma
commited on
Jul 24, 2023
add torch_dtype="auto" to load model weights in bf16
a9e1351
rskuzma
commited on
Jul 24, 2023
inference widget off
42c85d6
rskuzma
commited on
Jul 24, 2023
revert changes for hf endpoint handler
5fa5dd7
Faisal AlKhateeb
commited on
Jul 24, 2023
point to svg for long msl image
77bf4f1
rskuzma
commited on
Jul 24, 2023
upload svg for long msl xentropy
cb7fba3
rskuzma
commited on
Jul 24, 2023
add hf endpoint handler
70c7ea4
Faisal AlKhateeb
commited on
Jul 24, 2023
inference widget
eff5217
rskuzma
commited on
Jul 24, 2023
update README, slight revisions and typos (
#5
)
287d8f9
rskuzma
commited on
Jul 24, 2023
fix three images (
#4
)
908e05c
rskuzma
commited on
Jul 24, 2023
update license and inference widget
09c2924
rskuzma
commited on
Jul 24, 2023
update blog link
3e954b4
rskuzma
commited on
Jul 24, 2023
add README (
#3
)
e2b82a1
rskuzma
commited on
Jul 24, 2023
upload images from blog (
#2
)
2f0d2d8
rskuzma
commited on
Jul 24, 2023
change mup param names
eb4f0e4
Faisal AlKhateeb
commited on
Jul 21, 2023
add bfloat16 checkpoint
19c3116
Faisal AlKhateeb
commited on
Jul 21, 2023
add the tokenizer
326d150
Faisal AlKhateeb
commited on
Jul 19, 2023
add checkpoint
6317e26
Faisal AlKhateeb
commited on
Jul 19, 2023
add model files
2c2d81f
Faisal AlKhateeb
commited on
Jul 19, 2023
initial commit
dd1bb13
rskuzma
commited on
Jul 14, 2023