blob: 69eb5129bc963de153a6ece37433433aa0f3ba86 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
|
cd /mnt/data/lyzhuang/linear-rag
# medical
# SPACY_MODEL="en_core_sci_scibert"
# EMBEDDING_MODEL="model/all-mpnet-base-v2"
# DATASET="medical"
# LLM_MODEL="gpt-4o-mini"
# MAX_WORKERS=16
# MAX_ITERATION=3
# PASSAGE_RATIO=1.5
# THRESHOLD=0.5
# TOP_K_SENTENCE=1
# musique
# SPACY_MODEL="en_core_web_trf"
# EMBEDDING_MODEL="model/all-mpnet-base-v2"
# DATASET="musique"
# LLM_MODEL="gpt-4o-mini"
# MAX_WORKERS=16
# MAX_ITERATION=5
# PASSAGE_RATIO=2.0
# THRESHOLD=0.1
# TOP_K_SENTENCE=4
# 2wikimultihop
# SPACY_MODEL="en_core_web_trf"
# EMBEDDING_MODEL="model/all-mpnet-base-v2"
# DATASET="2wikimultihop"
# LLM_MODEL="gpt-4o-mini"
# MAX_WORKERS=16
# MAX_ITERATION=3
# PASSAGE_RATIO=0.05
# THRESHOLD=0.4
# TOP_K_SENTENCE=1
# hotpotqa
# SPACY_MODEL="en_core_web_trf"
# EMBEDDING_MODEL="model/all-mpnet-base-v2"
# DATASET="hotpotqa"
# LLM_MODEL="gpt-4o-mini"
# MAX_WORKERS=16
# MAX_ITERATION=3
# PASSAGE_RATIO=0.05
# THRESHOLD=0.4
# TOP_K_SENTENCE=1
python run.py \
--spacy_model ${SPACY_MODEL} \
--embedding_model ${EMBEDDING_MODEL} \
--dataset_name ${DATASET} \
--llm_model ${LLM_MODEL} \
--max_workers ${MAX_WORKERS} \
--max_iterations ${MAX_ITERATION} \
--iteration_threshold ${THRESHOLD} \
--passage_ratio ${PASSAGE_RATIO} \
--top_k_sentence ${TOP_K_SENTENCE}
|
