Downloads · 30 days
6
19% of all-time downloads
yinita/gigpo-multi-topo-sync2-w3c20-0729-central-step20
gigpo-multi-topo-sync2-w3c20-0729-central-step20 is a machine learning model from yinita. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter from multi-topology GiGPO run gigpomultitoposync2w3c2007291034 at step 20 (topology block: central).
Downloads · 30 days
6
19% of all-time downloads
All-time downloads
31
Public
Repo size
116 MB
Likes
0
Public
Click a slice to open those files.
.safetensors116 MB · 100%
From the Hugging Face model README
LoRA adapter from multi-topology GiGPO run gigpo_multi_topo_sync2_w3c20_0729_1034 at step 20 (topology block: central).
yinita/ps4mas-sft-x5-single-ep3acq_w=3, comp_w=20), reward_phase1_steps=0sync-every=2, force_acquire_frac=0, max_steps=50| repo | step | topo | CS composite | CS acq |
|---|---|---|---|---|
yinita/gigpo-multi-topo-sync2-w3c20-0729-single-step10 | 10 | single | 2.666 | 0.10 |
yinita/gigpo-multi-topo-sync2-w3c20-0729-central-step20 | 20 | central | 2.498 | 0.70 |
yinita/gigpo-multi-topo-sync2-w3c20-0729-hier-step30 | 30 | hier | 3.100 | 0.70 |
yinita/gigpo-multi-topo-sync2-w3c20-0729-debate-step40 | 40 | debate | 2.666 | 0.60 |
yinita/gigpo-multi-topo-sync2-w3c20-0729-single-step50 | 50 | single | 2.566 | 0.30 |
Adapter-only (no optimizer). Load as LoRA on the SFT base (e.g. vLLM --enable-lora).