Update README.md
Browse files
README.md
CHANGED
@@ -32,6 +32,8 @@ It should be noted that hypotheses and premises are randomly chosen between Engl
|
|
32 |
|
33 |
### Benchmark
|
34 |
|
|
|
|
|
35 |
| **model** | **accuracy (%)** | **MCC (x100)** |
|
36 |
| :--------------: | :--------------: | :------------: |
|
37 |
| [cmarkea/distilcamembert-base-nli](https://huggingface.co/cmarkea/distilcamembert-base-nli) | 77.45 | 66.24 |
|
@@ -41,6 +43,10 @@ It should be noted that hypotheses and premises are randomly chosen between Engl
|
|
41 |
| [cmarkea/bloomz-3b-nli](https://huggingface.co/cmarkea/bloomz-3b-nli) | 81.08 | 71.66 |
|
42 |
| [cmarkea/bloomz-7b1-mt-nli](https://huggingface.co/cmarkea/bloomz-7b1-mt-nli) | 83.13 | 74.89 |
|
43 |
|
|
|
|
|
|
|
|
|
44 |
# Zero-shot Classification
|
45 |
The primary appeal of training such models lies in their zero-shot classification performance. This means the model is capable of classifying any text with any label
|
46 |
without specific training. What sets the Bloomz-560m-NLI LLMs apart in this realm is their ability to model and extract information from significantly more complex
|
|
|
32 |
|
33 |
### Benchmark
|
34 |
|
35 |
+
Here are the performances for the hypothesis and premise in French:
|
36 |
+
|
37 |
| **model** | **accuracy (%)** | **MCC (x100)** |
|
38 |
| :--------------: | :--------------: | :------------: |
|
39 |
| [cmarkea/distilcamembert-base-nli](https://huggingface.co/cmarkea/distilcamembert-base-nli) | 77.45 | 66.24 |
|
|
|
43 |
| [cmarkea/bloomz-3b-nli](https://huggingface.co/cmarkea/bloomz-3b-nli) | 81.08 | 71.66 |
|
44 |
| [cmarkea/bloomz-7b1-mt-nli](https://huggingface.co/cmarkea/bloomz-7b1-mt-nli) | 83.13 | 74.89 |
|
45 |
|
46 |
+
And now the hypothesis in French and the premise in English (cross-language context):
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
# Zero-shot Classification
|
51 |
The primary appeal of training such models lies in their zero-shot classification performance. This means the model is capable of classifying any text with any label
|
52 |
without specific training. What sets the Bloomz-560m-NLI LLMs apart in this realm is their ability to model and extract information from significantly more complex
|