Edit model card

Public version of our 3b-model trained to perform 9 specific task in english and french with high accuracy. The benchmark bellow is done with our evaluation pipeline.

Model Fine-tune from meta-llama/Llama-3.2-3B-Instruct with a specific LoRA adapter.

+--------------------------------------------------+---------+------------+------------+
| llama3b_lora_long_llama3b_lora_long_filtered_310 | Overall | Team score | loads fail |
+--------------------------------------------------+---------+------------+------------+
|               answer_reformulation               |   0.73  |    0.68    |    0.95    |
|               query_reformulation                |   0.83  |    1.0     |    142     |
|                  summarization                   |   0.92  |    ---     |     23     |
|                keyword_extraction                |   0.77  |    ---     |     65     |
|                fill_in_generation                |   0.84  |    ---     |     14     |
|                  keyword_update                  |   0.64  |    0.8     |     12     |
|                       gqa                        |   0.79  |    0.64    |     15     |
|                    true_false                    |   0.76  |    ---     |    170     |
|                       mcq                        |   0.85  |    ---     |     41     |
|                      Total                       |   0.79  |    ---     |   482.95   |
+--------------------------------------------------+---------+------------+------------+

W&B Chart 22_11_2024 15_16_37.svg

Downloads last month
3
Safetensors
Model size
3.21B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.