Commit
•
63305c2
1
Parent(s):
56edee3
Upload sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 ctranslate2 weights
Browse files- README.md +8 -4
- model.bin +2 -2
- vocabulary.txt +0 -0
README.md
CHANGED
@@ -16,7 +16,7 @@ Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on
|
|
16 |
|
17 |
quantized version of [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
|
18 |
```bash
|
19 |
-
pip install hf-hub-ctranslate2>=2.12.0 ctranslate2>=3.
|
20 |
```
|
21 |
|
22 |
```python
|
@@ -56,16 +56,20 @@ embeddings = model.encode(
|
|
56 |
print(embeddings.shape, embeddings)
|
57 |
scores = (embeddings @ embeddings.T) * 100
|
58 |
|
|
|
|
|
|
|
|
|
59 |
```
|
60 |
|
61 |
-
Checkpoint compatible to [ctranslate2>=3.
|
62 |
and [hf-hub-ctranslate2>=2.12.0](https://github.com/michaelfeil/hf-hub-ctranslate2)
|
63 |
- `compute_type=int8_float16` for `device="cuda"`
|
64 |
- `compute_type=int8` for `device="cpu"`
|
65 |
|
66 |
-
Converted on 2023-
|
67 |
```
|
68 |
-
|
69 |
```
|
70 |
|
71 |
# Licence and other remarks:
|
|
|
16 |
|
17 |
quantized version of [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
|
18 |
```bash
|
19 |
+
pip install hf-hub-ctranslate2>=2.12.0 ctranslate2>=3.17.1
|
20 |
```
|
21 |
|
22 |
```python
|
|
|
56 |
print(embeddings.shape, embeddings)
|
57 |
scores = (embeddings @ embeddings.T) * 100
|
58 |
|
59 |
+
# Hint: you can also host this code via REST API and
|
60 |
+
# via github.com/michaelfeil/infinity
|
61 |
+
|
62 |
+
|
63 |
```
|
64 |
|
65 |
+
Checkpoint compatible to [ctranslate2>=3.17.1](https://github.com/OpenNMT/CTranslate2)
|
66 |
and [hf-hub-ctranslate2>=2.12.0](https://github.com/michaelfeil/hf-hub-ctranslate2)
|
67 |
- `compute_type=int8_float16` for `device="cuda"`
|
68 |
- `compute_type=int8` for `device="cpu"`
|
69 |
|
70 |
+
Converted on 2023-10-13 using
|
71 |
```
|
72 |
+
LLama-2 -> removed <pad> token.
|
73 |
```
|
74 |
|
75 |
# Licence and other remarks:
|
model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c59f14a4df4ce59c1b82b6438ba6d3fbf5cb744ec3c9d49efab61cec2ea9425
|
3 |
+
size 235315884
|
vocabulary.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|