MatthewCYM

Hi, Thank you for your impressive work. I try to reproduce the results of SAN and GatedGCN on PATTERN using GraphGPS framework. The results are all around 89.9 test accuracy,...

Hi, I try to extend the graphormer through adding a GIN model (ogb implementaion) for hiv task. The model currently works fine on the cpu. However, when I use gpu...

Support for GPTQ-LLAMA

1

Hi, Can I use GPTQ quantized model to do the inference? ``` https://github.com/qwopqwop200/GPTQ-for-LLaMa ``` Thank you!

Hi, May I ask if you have tried to train an unsupervised roberta sentence embedding? Thank you!

Conditional Generation

1

Hi @Hzfinfdu, May I ask where can I find more details about conditional generation? Thank you!

Hi @JetRunner, May I ask what's the regression threshold for STS-B and evaluation metrics for each task? Thank you!

Hi @LeeSureman , I am a bit confused with the modeling_bert_ee code. If the training mode is 'joint_sample_copy' as in further_train stage: The loss will computed in the if branch...

Unable to reproduce the results

13

I tried to reproduce the results on GLUE benchmark. I got F1 score 66 on MPRC, which is much lower than the one reported in the paper(78). I also got...

Hi @Dejiao2018 May I ask where can I find the file hwu64_label2id.json? Thank you!

Fail to load fixie-ai/ultravox-v0_4_1-llama-3_1-70b with device_map 'auto'

3

Hi, When I load the model into 4 gpus with model parallelism: ``` transformers.pipeline(model='fixie-ai/ultravox-v0_4_1-llama-3_1-70b', trust_remote_code=True, device_map='auto') ``` It gives the below error: ``` ValueError: weight is on the meta device,...