Merge pull request #3261 from khazic/main
Added specimens for single-card full parameter prediction
This commit is contained in:
commit
09735ed30c
|
@ -22,6 +22,7 @@ examples/
|
|||
├── full_multi_gpu/
|
||||
│ ├── single_node.sh: 使用 DeepSpeed 进行单节点训练
|
||||
│ └── multi_node.sh: 使用 DeepSpeed 进行多节点训练
|
||||
| └── predict.sh: 使用单卡做全参批量预测
|
||||
├── merge_lora/
|
||||
│ ├── merge.sh: 将 LoRA 权重合并到预训练模型中
|
||||
│ └── quantize.sh: 使用 AutoGPTQ 量化模型
|
||||
|
|
|
@ -0,0 +1,18 @@
|
|||
#!/bin/bash
|
||||
|
||||
CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
|
||||
--stage sft \
|
||||
--do_predict \
|
||||
--model_name_or_path meta-llama/Llama-2-7b-hf \
|
||||
--dataset alpaca_gpt4_en,glaive_toolcall \
|
||||
--dataset_dir ../../data \
|
||||
--template default \
|
||||
--finetuning_type full \
|
||||
--output_dir ../../saves/LLaMA2-7B/full/predict \
|
||||
--overwrite_cache \
|
||||
--overwrite_output_dir \
|
||||
--cutoff_len 1024 \
|
||||
--preprocessing_num_workers 16 \
|
||||
--per_device_eval_batch_size 1 \
|
||||
--max_samples 20 \
|
||||
--predict_with_generate
|
Loading…
Reference in New Issue