Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ model-index:
|
|
| 19 |
args: iso-eng
|
| 20 |
dataset:
|
| 21 |
name: flores101-devtest
|
| 22 |
-
type:
|
| 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}
|