v1.0.1

d99506f3 · chenzk · 61e92904 · d99506f3 · d99506f3 · d99506f3
Commit d99506f3 authored Dec 03, 2024 by chenzk
20 changed files
--- a/generation/sampler.py
+++ b/generation/sampler.py
--- a/helpers.py
+++ b/helpers.py
--- a/logging.py
+++ b/logging.py
--- a/models/__init__.py
+++ b/models/__init__.py
--- a/models/base.py
+++ b/models/base.py
--- a/models/llama.py
+++ b/models/llama.py
--- a/models/starcoder2.py
+++ b/models/starcoder2.py
--- a/src/nanotron/nn/__init__.py
+++ b/src/nanotron/nn/__init__.py
--- a/nn/activations.py
+++ b/nn/activations.py
--- a/nn/layer_norm.py
+++ b/nn/layer_norm.py
--- a/optim/__init__.py
+++ b/optim/__init__.py
--- a/optim/base.py
+++ b/optim/base.py
--- a/optim/clip_grads.py
+++ b/optim/clip_grads.py
--- a/optim/gradient_accumulator.py
+++ b/optim/gradient_accumulator.py
--- a/optim/inherit_from_other_optimizer.py
+++ b/optim/inherit_from_other_optimizer.py
--- a/optim/named_optimizer.py
+++ b/optim/named_optimizer.py
--- a/optim/optimizer_from_gradient_accumulator.py
+++ b/optim/optimizer_from_gradient_accumulator.py
--- a/optim/zero.py
+++ b/optim/zero.py
--- a/parallel/__init__.py
+++ b/parallel/__init__.py
--- a/parallel/context.py
+++ b/parallel/context.py