| .. |
|
__init__.py
|
c2aaaefd57
allow out-of-tree model registry
|
9 달 전 |
|
baichuan.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
bloom.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
chatglm.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
cohere.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
dbrx.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
decilm.py
|
e31c6f0b45
feat: refactor modeling logic and support more models (#274)
|
11 달 전 |
|
deepseek.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
falcon.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
gemma.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
gpt2.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
gpt_bigcode.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
gpt_j.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
gpt_neox.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
internlm2.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
llama.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
llava.py
|
4d33ce60da
feat: Triton flash attention backend for ROCm (#407)
|
9 달 전 |
|
mixtral.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
mpt.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
olmo.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
opt.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
phi.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
qwen.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
qwen2.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
qwen2moe.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
|
stablelm.py
|
50c2434267
move megatron to a top-level directory
|
9 달 전 |
AlpinDale
50c2434267
move megatron to a top-level directory