not-lain commited on
Commit
f2ef0c1
1 Parent(s): c78cfaf

Update README.md

Browse files

this pr includes
* fix img embeddings
* better markdown for python codes

Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -6,7 +6,7 @@ tags:
6
  - ColBERT
7
  ---
8
  <p align="center">
9
- <img align="center" src="docs/images/colbertofficial.png" width="430px" />
10
  </p>
11
  <p align="left">
12
 
@@ -18,7 +18,7 @@ tags:
18
 
19
 
20
  <p align="center">
21
- <img align="center" src="docs/images/ColBERT-Framework-MaxSim-W370px.png" />
22
  </p>
23
  <p align="center">
24
  <b>Figure 1:</b> ColBERT's late interaction, efficiently scoring the fine-grained similarity between a queries and a passage.
@@ -107,7 +107,7 @@ For fast retrieval, indexing precomputes the ColBERT representations of passages
107
 
108
  Example usage:
109
 
110
- ```
111
  from colbert.infra import Run, RunConfig, ColBERTConfig
112
  from colbert import Indexer
113
 
@@ -127,7 +127,7 @@ if __name__=='__main__':
127
 
128
  We typically recommend that you use ColBERT for **end-to-end** retrieval, where it directly finds its top-k passages from the full collection:
129
 
130
- ```
131
  from colbert.data import Queries
132
  from colbert.infra import Run, RunConfig, ColBERTConfig
133
  from colbert import Searcher
@@ -161,7 +161,7 @@ Training requires a JSONL triples file with a `[qid, pid+, pid-]` list per line.
161
 
162
  Example usage (training on 4 GPUs):
163
 
164
- ```
165
  from colbert.infra import Run, RunConfig, ColBERTConfig
166
  from colbert import Trainer
167
 
 
6
  - ColBERT
7
  ---
8
  <p align="center">
9
+ <img align="center" src="https://github.com/stanford-futuredata/ColBERT/blob/main/docs/images/colbertofficial.png?raw=true" width="430px" />
10
  </p>
11
  <p align="left">
12
 
 
18
 
19
 
20
  <p align="center">
21
+ <img align="center" src="https://github.com/stanford-futuredata/ColBERT/blob/main/docs/images/ColBERT-Framework-MaxSim-W370px.png?raw=true" />
22
  </p>
23
  <p align="center">
24
  <b>Figure 1:</b> ColBERT's late interaction, efficiently scoring the fine-grained similarity between a queries and a passage.
 
107
 
108
  Example usage:
109
 
110
+ ```python
111
  from colbert.infra import Run, RunConfig, ColBERTConfig
112
  from colbert import Indexer
113
 
 
127
 
128
  We typically recommend that you use ColBERT for **end-to-end** retrieval, where it directly finds its top-k passages from the full collection:
129
 
130
+ ```python
131
  from colbert.data import Queries
132
  from colbert.infra import Run, RunConfig, ColBERTConfig
133
  from colbert import Searcher
 
161
 
162
  Example usage (training on 4 GPUs):
163
 
164
+ ```python
165
  from colbert.infra import Run, RunConfig, ColBERTConfig
166
  from colbert import Trainer
167