LLM Name | Cap Iaa Lora Attn |
Repository ๐ค | https://huggingface.co/kkeezz/cap-iaa-lora-attn |
Required VRAM | 0.2 GB |
Updated | 2024-08-15 |
Maintainer | kkeezz |
Model Files | |
Model Architecture | Adapter |
Is Biased | none |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | model.layers.18.self_attn.v_proj.multiway.1|model.layers.14.self_attn.v_proj.multiway.1|model.layers.27.self_attn.q_proj|model.layers.2.self_attn.q_proj|model.layers.4.self_attn.q_proj|model.layers.18.self_attn.q_proj|model.layers.7.self_attn.q_proj|model.layers.5.self_attn.q_proj|model.layers.15.self_attn.q_proj|model.layers.7.self_attn.v_proj.multiway.1|model.layers.6.self_attn.v_proj.multiway.1|model.layers.12.self_attn.v_proj.multiway.1|model.layers.16.self_attn.q_proj|model.layers.31.self_attn.q_proj|model.layers.17.self_attn.q_proj|model.layers.10.self_attn.q_proj|model.layers.22.self_attn.q_proj|model.layers.3.self_attn.v_proj.multiway.1|model.layers.23.self_attn.q_proj|model.layers.9.self_attn.v_proj.multiway.1|model.layers.13.self_attn.q_proj|model.layers.4.self_attn.v_proj.multiway.1|model.layers.11.self_attn.v_proj.multiway.1|model.layers.19.self_attn.v_proj.multiway.1|model.layers.21.self_attn.q_proj|model.layers.26.self_attn.q_proj|model.layers.28.self_attn.v_proj.multiway.1|model.layers.20.self_attn.q_proj|model.layers.31.self_attn.v_proj.multiway.1|model.layers.0.self_attn.q_proj|model.layers.24.self_attn.v_proj.multiway.1|model.layers.30.self_attn.q_proj|model.layers.5.self_attn.v_proj.multiway.1|model.layers.17.self_attn.v_proj.multiway.1|model.layers.27.self_attn.v_proj.multiway.1|model.layers.13.self_attn.v_proj.multiway.1|model.layers.6.self_attn.q_proj|model.layers.12.self_attn.q_proj|model.layers.25.self_attn.q_proj|model.layers.2.self_attn.v_proj.multiway.1|model.layers.1.self_attn.q_proj|model.layers.10.self_attn.v_proj.multiway.1|model.layers.29.self_attn.v_proj.multiway.1|model.layers.30.self_attn.v_proj.multiway.1|model.layers.3.self_attn.q_proj|model.layers.26.self_attn.v_proj.multiway.1|model.layers.8.self_attn.v_proj.multiway.1|model.layers.8.self_attn.q_proj|model.layers.11.self_attn.q_proj|model.layers.20.self_attn.v_proj.multiway.1|model.layers.24.self_attn.q_proj|model.layers.23.self_attn.v_proj.multiway.1|model.layers.28.self_attn.q_proj|model.layers.9.self_attn.q_proj|model.layers.14.self_attn.q_proj|model.layers.22.self_attn.v_proj.multiway.1|model.layers.19.self_attn.q_proj|model.layers.21.self_attn.v_proj.multiway.1|model.layers.15.self_attn.v_proj.multiway.1|model.layers.29.self_attn.q_proj|model.layers.16.self_attn.v_proj.multiway.1|model.layers.0.self_attn.v_proj.multiway.1|model.layers.25.self_attn.v_proj.multiway.1|model.layers.1.self_attn.v_proj.multiway.1 |
LoRA Alpha | 256 |
LoRA Dropout | 0.05 |
R Param | 128 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Tot Llama Update | 0K / 0 GB | 2310 | 0 |
Ll3 C3 Lora New | 0K / 0 GB | 7 | 0 |
Zephyr Phi 1 5 Sft Qlora | 0K / 0 GB | 5 | 0 |
Phi Openllm Lb Test | 0K / 0 GB | 5 | 0 |
Hua V0.1 | 0K / 0 GB | 6 | 0 |
CodeHAWK | 0K / 0 GB | 8 | 0 |
....001 0.5ultrafeedback LowLr I1 | 0K / 0 GB | 7 | 0 |
...ew2 B0.001 0.5ultrafeedback I1 | 0K / 0 GB | 5 | 0 |
Phi 2 Gpo Renew2 B0.001 V4 I1 | 0K / 0.2 GB | 5 | 0 |
Absa 10 Domains Large | 0K / 0.1 GB | 6 | 0 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐