abcdabcd987
2 models • 1 total models in database
Sort by:
gsm8k-llama2-7b-lora-16
NaNK
llama-factory
0
6
Sqlctx Llama2 7b Lora 16
Punica: Serving multiple LoRA finetuned LLMs at the cost of one Base Model: Llama-2-7b-hf LoRA target: `qproj,kproj,vproj,oproj,gateproj,upproj,downproj` LoRA rank: 16 The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 32 - evalbatchsize: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: cosine - numepochs: 4.0 - Transformers 4.34.1 - Pytorch 2.2.0.dev20230911+cu121 - Datasets 2.14.4 - Tokenizers 0.14.1
NaNK
llama-factory
0
1