Zikun Xu

> @xuzikun2003 no its not currently supported if you want each topic to go to a separate influxdb. PRs welcome! But how would you handle credentials per db in KCQL...

> @xuzikun2003 In your example you would have too many measurements and only one field for each measurement in InfluxDB which is not a good [schema design](https://docs.influxdata.com/influxdb/v1.8/concepts/schema_and_data_layout/). > > Trying...

> However see also #329, if the name of the keys `key1`, `key2`, `key3` are fixed you could try a KSQL query like this: > > ``` > connect.influx.kcql="INSERT INTO...

I would like to pick up this work and here is the design doc https://docs.google.com/document/d/1C7_BT1kIF8Z2YJXioPUSg5J0yfDEfN5g5zYtcZW2Nx8/edit?usp=sharing

Should I do something like this? from transformers import AutoTokenizer, AutoModel, AutoConfig from sat.training.model_io import save_checkpoint config = AutoConfig.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True) args = argparse.Namespace( num_layers=config.num_layers, vocab_size=config.vocab_size, hidden_size=config.hidden_size, num_attention_heads=config.num_attention_heads, max_sequence_length=config.max_sequence_length, bos_token_id=tokenizer.bos_token_id, mask_token_id=tokenizer.mask_token_id,...

> We don't have visualglm-6b/300. I don't know what code you are running. I ran the q-lora fine tuning script. bash finetune/finetune_visualglm_qlora.sh and got the above error.