gistfile1.txt

https://app.cnvrg-prd.pg.wwtatc.ai/users/sign_up?email=craig.smith%40cnvrg.io&invite_code=pPzxpptz5hJefL5Rxn9M

HF_TOKEN="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" python3 gaudi_spawn.py --world_size 8 --use_deepspeed language-modeling/run_lora_clm.py \
   --model_name_or_path meta-llama/Llama-2-7b-hf \
   --dataset_name tatsu-lab/alpaca \
   --bf16 True \
   --output_dir ./model_peft_output \
   --num_train_epochs 1 \
   --per_device_train_batch_size 2 \
   --per_device_eval_batch_size 2 \
   --gradient_accumulation_steps 4 \
   --evaluation_strategy no \
   --save_strategy steps \
   --save_steps 2000 \
   --save_total_limit 1 \
   --learning_rate 1e-4 \
   --logging_steps 1 \
   --dataset_concatenation \
   --do_train \
   --use_habana \
   --distribution_strategy fast_ddp \
   --use_lazy_mode \
   --throughput_warmup_steps 3
   
   python3 run_lora_clm.py \
    --model_name_or_path meta-llama/Llama-2-7b-hf \
    --dataset_name tatsu-lab/alpaca \
    --bf16 True \
    --output_dir ./model_lora_llama \
    --num_train_epochs 3 \
    --per_device_train_batch_size 2 \
    --per_device_eval_batch_size 2 \
    --gradient_accumulation_steps 4 \
    --evaluation_strategy no \
    --save_strategy steps \
    --save_steps 2000 \
    --save_total_limit 1 \
    --learning_rate 1e-4 \
    --logging_steps 1 \
    --dataset_concatenation \
    --do_train \
    --use_habana \
    --use_lazy_mode \
    --throughput_warmup_steps 1
   
   daniatalla/gaudi_pytorch:dl2_1.14
   
   python3 model_utils.py predict_stream \
        --base_model_path meta-llama/Llama-2-7b-hf \
        --peft_model_path /intel-extension-for-transformers/optimum-habana/examples/language-modeling/model_lora_llama \
        --habana \
        --device hpu \
        --use_hpu_graphs \
        --use_kv_cache \
        --jit \
        --instructions "What is the tallest building in the world"
        
python run_clm.py \
    --model_name_or_path meta-llama/Llama-2-7b-hf \
    --dataset_name tatsu-lab/alpaca \
    --dataset_config_name tatsu-lab/alpaca \
    --per_device_eval_batch_size 4 \
    --do_eval \
    --output_dir ./new_model \
    --gaudi_config_name Habana/gpt2 \
    --use_habana \
    --use_lazy_mode \
    --use_hpu_graphs_for_inference \
    --bf16
    
python run_generation.py \
--model_name_or_path gpt2 \
--use_hpu_graphs \
--use_kv_cache \
--max_new_tokens 100 \
--do_sample \
--prompt "Here is my prompt"