Commit
•
631cdef
1
Parent(s):
83f61eb
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,20 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# SmolLM-135M-ft-ary
|
| 2 |
|
| 3 |
-
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on the Fineweb dataset.
|
| 4 |
-
It achieves the following results on the evaluation set:
|
| 5 |
-
- Loss: 1.7018
|
| 6 |
-
|
| 7 |
### Model Description
|
| 8 |
|
| 9 |
<!-- Provide a longer summary of what this model is. -->
|
| 10 |
-
|
| 11 |
-
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 12 |
|
| 13 |
- **Developed by:** EL MAJJODI Abdeljalil & Omneity Labs team
|
| 14 |
- **Model type:** Text Generation
|
| 15 |
- **Language(s) (NLP):** Darija (Arabic-ary)
|
| 16 |
- **Finetuned from model:** HuggingFaceTB/SmolLM-135M
|
| 17 |
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Training procedure
|
| 20 |
|
|
@@ -41,4 +47,4 @@ The following hyperparameters were used during training:
|
|
| 41 |
- Transformers 4.47.0
|
| 42 |
- Pytorch 2.1.1+cu121
|
| 43 |
- Datasets 3.1.0
|
| 44 |
-
- Tokenizers 0.21.0
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- sawalni-ai/fw-darija
|
| 4 |
+
language:
|
| 5 |
+
- ar
|
| 6 |
+
base_model:
|
| 7 |
+
- HuggingFaceTB/SmolLM-135M
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
---
|
| 10 |
# SmolLM-135M-ft-ary
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
### Model Description
|
| 13 |
|
| 14 |
<!-- Provide a longer summary of what this model is. -->
|
| 15 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on the [sawalni-ai/fineweb-arabic-base](https://huggingface.co/sawalni-ai/fineweb-arabic-base) dataset.
|
|
|
|
| 16 |
|
| 17 |
- **Developed by:** EL MAJJODI Abdeljalil & Omneity Labs team
|
| 18 |
- **Model type:** Text Generation
|
| 19 |
- **Language(s) (NLP):** Darija (Arabic-ary)
|
| 20 |
- **Finetuned from model:** HuggingFaceTB/SmolLM-135M
|
| 21 |
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- **Loss**: 1.7018
|
| 24 |
|
| 25 |
## Training procedure
|
| 26 |
|
|
|
|
| 47 |
- Transformers 4.47.0
|
| 48 |
- Pytorch 2.1.1+cu121
|
| 49 |
- Datasets 3.1.0
|
| 50 |
+
- Tokenizers 0.21.0
|