yujunjun/FlagEmbedding
1
0
Fork 0
mirror of https://github.com/FlagOpen/FlagEmbedding.git synced 2026-01-07 04:33:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README

Browse Source
This commit is contained in:
namespace-Pt 2023-10-11 11:03:00 +00:00
parent 7dbb8e350e
commit bfdb057338
2 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
FlagEmbedding/llm_embedder/docs/fine-tune.md
View File

@ -124,14 +124,14 @@ torchrun --nproc_per_node=8 run_dense.py \
### Mine Negatives
```bash
# BGE
# BGE (the result will be saved at llm-embedder:qa/nq/train.bge.json)
torchrun --nproc_per_node=8 -m evaluation.eval_retrieval \
--eval_data llm-embedder:qa/nq/train.json \
--corpus llm-embedder:qa/nq/corpus.json \
--metrics mrr recall collate_neg \
--save_name bge
# BM25
# BM25 (the result will be saved at llm-embedder:qa/nq/train.bm25.json)
torchrun --nproc_per_node 8 -m evaluation.eval_retrieval \
--retrieval_method bm25 \
--eval_data llm-embedder:qa/nq/train.json \

1
FlagEmbedding/llm_embedder/evaluation/eval_lrlm.py
View File

@ -61,6 +61,7 @@ class LRLMArgs(RetrievalArgs, SRLMArgs):
)
def __post_init__(self):
super().__post_init__()
if self.retrieval_method == "bm25":
# NOTE: we can only use naive bm25 for self retrieval
self.retrieval_method = "naive-bm25"