TencentARC / ST-LLM

Official implementation of the paper "ST-LLM: Large Language Models Are Effective Temporal Learners"

TencentARC/ST-LLM Issues

how to modify the code to support llama3?
Closed 8 days ago1
How to fine-tune on image data
Closed 9 days ago4
微调过程中loss问题
Updated 20 days ago2
what's the difference between get_context_emb() and get_context_emb_sim()?
Closed 19 days ago1
Some weights of the model checkpoint at stllm/output/instructblipbase_stllm_conversation/ were not used?
Updated 20 days ago1
Training Time Discrepancies
Updated a month ago1
The specific settings of Lora finetuning
Updated 20 days ago5
MVbench的测试情况
Updated a month ago6
MVM loss
Closed a month ago4
HF weights
Closed a month ago2
Cuda Version
Closed a month ago1
Release the inference result of the benchmark
Closed 2 months ago1
Question about eval
Closed 2 months ago2
MVBench测试结果不一致
Closed 2 months ago5
Questions about the testing strategy
Closed 2 months ago2