Pinned Repositories
gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
Large-MTJ
This is a modified version of https://github.com/VE-FORBRYDERNE/mesh-transformer-jax/tree/ck to be adapted to JAX 0.3.25 so this runs on colab with TPU_driver0.2
mesh-transformer-jax
Model parallel transformers in JAX and Haiku
mesh-transformer-jax10
v2
mesh-transformer-jax11
shmap
mesh-transformer-jax12
jax 0.4.26
mesh-transformer-jax2
test for v2
mesh-transformer-jax3
test for v3
mesh-transformer-jax4
test for v3 jax0.3.25
mesh-transformer-jax5
test for v3 jax0.3.5 plain text
mosmos6's Repositories
mosmos6/gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
mosmos6/Large-MTJ
This is a modified version of https://github.com/VE-FORBRYDERNE/mesh-transformer-jax/tree/ck to be adapted to JAX 0.3.25 so this runs on colab with TPU_driver0.2
mosmos6/mesh-transformer-jax
Model parallel transformers in JAX and Haiku
mosmos6/mesh-transformer-jax10
v2
mosmos6/mesh-transformer-jax11
shmap
mosmos6/mesh-transformer-jax12
jax 0.4.26
mosmos6/mesh-transformer-jax2
test for v2
mosmos6/mesh-transformer-jax3
test for v3
mosmos6/mesh-transformer-jax4
test for v3 jax0.3.25
mosmos6/mesh-transformer-jax5
test for v3 jax0.3.5 plain text
mosmos6/mesh-transformer-jax6
jax4 core plus original
mosmos6/mesh-transformer-jax7
finetune test of jax4 repo
mosmos6/mesh-transformer-jax8
test
mosmos6/mesh-transformer-jax9
v5p
mosmos6/MTJ-on-TPU_driver0.2