Francesco Ferrari

BB3 RuntimeError: Need to set `model` argument to use create_agent.

3

**Bug description** Currently trying to fine-tune BB3 3B params but agent fails saying that `model` param is not passed. Command entered: `parlai train_model --search_decision compute --search_decision_do_search_reply search --search_server chatbot --memory_decision...

BB2 Agent's memory persistence on GPU even after calling `remove_agent`

4

I am trying to optimize my GPU's memory to able to have as many agents running at possible (each agent is a BB2 3B clone). I have noticed that each...

BB3 3B Runtime OOM Error on 40Gb GPU

9

**Bug description** Training on the 3B BB3 model fails due to OOM **Reproduction steps** - CUDA 11.6 - NVIDIA A100 (40GiB) Training command: `python3.8 -m parlai.scripts.multiprocessing_train -t custom_persona,msc --multitask-weights 8,2...

BB3 Unexpected reply behavior

12

**Bug description** BB3 seems to be acting on its own replies and provides a final answer that is based on the replies created by the memory and search agent. The...

BB3 training fails when using `projects.bb3.agents.r2c2_bb3_agent:BlenderBot3Agent` as model

2

**Bug description** Currently trying to train BB3 using the following command: ``` python3.8 -m parlai.scripts.train_model -t customchat_persona,msc --multitask-weights 3,1 -vstep 100000 -lstep 500 --batchsize 1 --validation-every-n-secs 1200 --validation-patience 20 --validation-max-exs...

InstructBlipProcessor not working with load_in_4bit and load_in_8bit

4

### System Info transformers @ git+https://github.com/huggingface/transformers@68c92981ff2b804979d2e6107eeefe298d1e5183 Python 3.11.4 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 510.47.03 Driver Version: 510.47.03 CUDA Version: 11.6 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC...