LB's picture

10

LB

lbathen

AI & ML interests

None yet

Recent Activity

new activity 25 days ago

Skywork/Skywork-Reward-Gemma-2-27B:Reward model returns 0 scores for all cases

View all activity

Organizations

None yet

lbathen's activity

New activity in Skywork/Skywork-Reward-Gemma-2-27B 25 days ago

Reward model returns 0 scores for all cases

#1 opened 4 months ago by

New activity in mgoin/Nemotron-4-340B-Instruct-hf 4 months ago

Reward model also possible?

#1 opened 5 months ago by

New activity in nvidia/Nemotron-4-340B-Base 4 months ago

Hf safetensors version

#3 opened 6 months ago by

New activity in nvidia/Nemotron-4-340B-Reward 5 months ago

Convertion to HF

#7 opened 5 months ago by

New activity in mistralai/Mistral-Nemo-Instruct-2407 5 months ago

NAN when training

#29 opened 5 months ago by

New activity in nvidia/Mistral-NeMo-12B-Instruct 5 months ago

Can't load model with nemo framework

#7 opened 5 months ago by

New activity in nvidia/Nemotron-4-340B-Reward 5 months ago

Running inference outside of triton

#6 opened 5 months ago by

New activity in mistralai/Mistral-Nemo-Instruct-2407 5 months ago

NeMo Format

#9 opened 5 months ago by

New activity in mistralai/Mixtral-8x22B-v0.1 6 months ago

Use V1 tokenizer instead

#10 opened 6 months ago by

vocab size mismatch

#9 opened 6 months ago by