DeepSpeedExamples
DeepSpeedExamples copied to clipboard
Example models using DeepSpeed
Deepspeed support finetune extra model with lora ?
Thanks for great work! When I run my inference code below using `deepspeed --include localhost:0,1,2 inference.py --model opt-iml-30b --dataset WQSP` I meet the error **exits with return code = -9**...
settings: actor & critic: OPT 1.3b reward model: OPT 350m GPU: 4 * V100 32G running script: ACTOR_MODEL_PATH=$1 CRITIC_MODEL_PATH=$2 ACTOR_ZERO_STAGE=$3 CRITIC_ZERO_STAGE=$4 OUTPUT=$5 if [ "$OUTPUT" == "" ]; then OUTPUT=./output...
Hi, I am trying to test the attention computation on the CPU with zero-interference. I use the following command to run the script. ``` BSZ=96 LOG_DIR=$BASE_LOG_DIR/${MODEL_NAME}_bs${BSZ} mkdir -p $LOG_DIR deepspeed...
I follow the instructions of this [page](https://github.com/microsoft/DeepSpeedExamples/tree/master/applications/DeepSpeed-Chat/training/step2_reward_model_finetuning) to do step2_reward_model_finetuning with demo code. On the Google Cloud platform, I create one instance with a single V100(16GB) and another instance with...
**Is your feature request related to a problem? Please describe.** We find that the generation stage of RLHF pipeline is time-consuming during the current training process. This is because the...
I'm trying to use DeepSpeed-Chat stage2 scripts to do rlhf with Qwen1.8b-chat model,I change some parts in dschat and main.py to load my model, the most different part is: ```...