Shitao commited on
Commit
47b5332
1 Parent(s): 2c0bb89

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -325,7 +325,8 @@ torchrun --nproc_per_node {number of gpus} \
325
  --target_modules q_proj k_proj v_proj o_proj \
326
  --start_layer 8 \
327
  --head_multi True \
328
- --head_type simple
 
329
  ```
330
 
331
  Our rerankers are initialized from [google/gemma-2b](https://huggingface.co/google/gemma-2b) (for llm-based reranker) and [openbmb/MiniCPM-2B-dpo-bf16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16) (for llm-based layerwise reranker), and we train it on a mixture of multilingual datasets:
 
325
  --target_modules q_proj k_proj v_proj o_proj \
326
  --start_layer 8 \
327
  --head_multi True \
328
+ --head_type simple \
329
+ --lora_extra_parameters linear_head
330
  ```
331
 
332
  Our rerankers are initialized from [google/gemma-2b](https://huggingface.co/google/gemma-2b) (for llm-based reranker) and [openbmb/MiniCPM-2B-dpo-bf16](https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16) (for llm-based layerwise reranker), and we train it on a mixture of multilingual datasets: