161 kB

Ctrl+K

3 contributors

History: 1 commit

mshahidul

Initial commit of readCtrl code without large models

030876e 8 days ago

agent_loop.rst

9.96 kB
Initial commit of readCtrl code without large models 8 days ago
async-on-policy-distill.md

13.5 kB
Initial commit of readCtrl code without large models 8 days ago
attention_implementation.rst

4.36 kB
Initial commit of readCtrl code without large models 8 days ago
checkpoint.rst

7.85 kB
Initial commit of readCtrl code without large models 8 days ago
dpo_extension.rst

9.71 kB
Initial commit of readCtrl code without large models 8 days ago
fp8.md

3.65 kB
Initial commit of readCtrl code without large models 8 days ago
fsdp_extension.rst

4.26 kB
Initial commit of readCtrl code without large models 8 days ago
fully_async.md

39.5 kB
Initial commit of readCtrl code without large models 8 days ago
grafana_prometheus.md

8.5 kB
Initial commit of readCtrl code without large models 8 days ago
megatron_extension.rst

766 Bytes
Initial commit of readCtrl code without large models 8 days ago
mtp.md

6.75 kB
Initial commit of readCtrl code without large models 8 days ago
one_step_off.md

14.9 kB
Initial commit of readCtrl code without large models 8 days ago
placement.rst

456 Bytes
Initial commit of readCtrl code without large models 8 days ago
ppo_lora.rst

10.6 kB
Initial commit of readCtrl code without large models 8 days ago
reward_loop.rst

14.3 kB
Initial commit of readCtrl code without large models 8 days ago
rollout_skip.rst

2.29 kB
Initial commit of readCtrl code without large models 8 days ago
rollout_trace.rst

8.83 kB
Initial commit of readCtrl code without large models 8 days ago
rope.rst

1.17 kB
Initial commit of readCtrl code without large models 8 days ago