Downloads · 30 days
9
19% of all-time downloads
kmseong/llama2_7b-chat-agnews-warp-kr0.1-lr3e-6-ep3-cb
llama2_7b-chat-agnews-warp-kr0.1-lr3e-6-ep3-cb is a machine learning model from kmseong. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama2.
kmseong/llama27b-chat-Safety-FT-lr5e-5 를 시작점으로, WaRP(Weight space Rotation Process) 재파라미터화 공간에서 안전 관련 계수 방향을 동결한 채 agnews 로 downstream fine-tuning 한 모델입니다.
Downloads · 30 days
9
19% of all-time downloads
All-time downloads
47
Public
Parameters
6.7B
13.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors13.5 GB · 100%
From the Hugging Face model README
kmseong/llama2_7b-chat-Safety-FT-lr5e-5 를 시작점으로, WaRP(Weight space Rotation Process) 재파라미터화 공간에서
안전 관련 계수 방향을 동결한 채 agnews 로 downstream fine-tuning 한 모델입니다.
U 로 회전 (C = W U)keep_ratio 좌표를 동결적용 범위: q_proj, k_proj, v_proj, up_proj, down_proj / 전체 32개 layer / per-layer 중요도.
| base model | kmseong/llama2_7b-chat-Safety-FT-lr5e-5 |
| downstream data | agnews (8000 samples) |
| epochs / lr | 3 / 3e-06 |
| batch x grad_accum | 2 x 8 (effective 16) |
| optimizer / scheduler | adamw_torch / cosine |
| coordinate space | - |
| frozen safety coefficients | - |
| train wall-clock | - s |
| train peak VRAM (device) | - GB |