radinplaid commited on
Commit
2a798e5
·
verified ·
1 Parent(s): a27927a

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +27 -12
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  args: iso-eng
20
  dataset:
21
  name: flores101-devtest
22
- type: flores_101
23
  args: isl_Latn eng_Latn devtest
24
  metrics:
25
  - name: BLEU
@@ -28,7 +28,21 @@ model-index:
28
  - name: CHRF
29
  type: chrf
30
  value: 60.91
31
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  ---
33
 
34
  <a href="https://huggingface.co/spaces/quickmt/quickmt-gui"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-lg-dark.svg" alt="Open in Spaces"></a>
@@ -100,18 +114,8 @@ The model is in `ctranslate2` format, and the tokenizers are `sentencepiece`, so
100
 
101
  Benchmarks are hard to get right and make fair. Download this model and give it a try and see if it works well for you!
102
 
103
-
104
  ### flores devtest
105
 
106
- | model | time | bleu | chrf |
107
- |----------------------------------|-------|-------|-------|
108
- | quickmt-is-en | 0.70 | 47.68 | 65.91 |
109
- | Helsinki-NLP/opus-mt-is-en | 1.17 | 36.46 | 56.62 |
110
- | facebook/nllb-200-distilled-1.3B | 8.57 | 40.31 | 60.39 |
111
- | CohereLabs/tiny-aya-global | 14.22 | 22.26 | 43.01 |
112
- | google/gemma-4-E2B-it | 23.79 | 36.90 | 57.52 |
113
-
114
- ### bouquet test
115
 
116
  | model | time | bleu | chrf |
117
  |----------------------------------|-------|-------|-------|
@@ -122,6 +126,17 @@ Benchmarks are hard to get right and make fair. Download this model and give it
122
  | google/gemma-4-E2B-it | 46.60 | 28.55 | 54.30 |
123
 
124
 
 
 
 
 
 
 
 
 
 
 
 
125
  Prompt for LLM translation:
126
 
127
  > Translate the following into {tgt_lang}, without commentary or explanation.\n\n{x}
 
19
  args: iso-eng
20
  dataset:
21
  name: flores101-devtest
22
+ type: translation
23
  args: isl_Latn eng_Latn devtest
24
  metrics:
25
  - name: BLEU
 
28
  - name: CHRF
29
  type: chrf
30
  value: 60.91
31
+ - task:
32
+ name: Translation isl-eng
33
+ type: translation
34
+ args: iso-eng
35
+ dataset:
36
+ name: bouquet
37
+ type: translation
38
+ args: isl_Latn eng_Latn test
39
+ metrics:
40
+ - name: BLEU
41
+ type: bleu
42
+ value: 47.68
43
+ - name: CHRF
44
+ type: chrf
45
+ value: 65.91
46
  ---
47
 
48
  <a href="https://huggingface.co/spaces/quickmt/quickmt-gui"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-lg-dark.svg" alt="Open in Spaces"></a>
 
114
 
115
  Benchmarks are hard to get right and make fair. Download this model and give it a try and see if it works well for you!
116
 
 
117
  ### flores devtest
118
 
 
 
 
 
 
 
 
 
 
119
 
120
  | model | time | bleu | chrf |
121
  |----------------------------------|-------|-------|-------|
 
126
  | google/gemma-4-E2B-it | 46.60 | 28.55 | 54.30 |
127
 
128
 
129
+ ### bouquet test
130
+
131
+ | model | time | bleu | chrf |
132
+ |----------------------------------|-------|-------|-------|
133
+ | quickmt-is-en | 0.70 | 47.68 | 65.91 |
134
+ | Helsinki-NLP/opus-mt-is-en | 1.17 | 36.46 | 56.62 |
135
+ | facebook/nllb-200-distilled-1.3B | 8.57 | 40.31 | 60.39 |
136
+ | CohereLabs/tiny-aya-global | 14.22 | 22.26 | 43.01 |
137
+ | google/gemma-4-E2B-it | 23.79 | 36.90 | 57.52 |
138
+
139
+
140
  Prompt for LLM translation:
141
 
142
  > Translate the following into {tgt_lang}, without commentary or explanation.\n\n{x}