Update README.md
Browse files
README.md
CHANGED
|
@@ -16,12 +16,6 @@ tags:
|
|
| 16 |
|
| 17 |
Calcium-Opus-14B-Elite3 is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. These models have proven effective in context understanding, reasoning, and mathematical problem-solving. It has been fine-tuned using a long chain-of-thought reasoning model and specialized datasets, with a focus on chain-of-thought (CoT) reasoning for problem-solving. This model is optimized for tasks requiring logical reasoning, detailed explanations, and multi-step problem-solving, making it ideal for applications such as instruction-following, text generation, and complex reasoning tasks.
|
| 18 |
|
| 19 |
-
# **Open-Evals**
|
| 20 |
-
|
| 21 |
-
| Rank | Model | Average | IFEval | BBH | MATH | GPQA | MUSR | MMLU | CO₂ Consumption | Dated |
|
| 22 |
-
| ---- | ----------------------------------------------------------------------------------------------------- | ------- | ------ | ----- | ----- | ----- | ----- | ----- | --------------- | ---------- |
|
| 23 |
-
| 108 | [prithivMLmods/Calcium-Opus-14B-Elite3](https://huggingface.co/prithivMLmods/Calcium-Opus-14B-Elite3) | 38.38 | 60.52 | 46.93 | 37.69 | 16.55 | 20.78 | 47.80 | 2.01 | 01/23/2025 |
|
| 24 |
-
|
| 25 |
Key improvements include:
|
| 26 |
|
| 27 |
1. **Enhanced Knowledge and Expertise**: The model demonstrates significantly more knowledge and greatly improved capabilities in coding and mathematics, thanks to specialized expert models in these domains.
|
|
|
|
| 16 |
|
| 17 |
Calcium-Opus-14B-Elite3 is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. These models have proven effective in context understanding, reasoning, and mathematical problem-solving. It has been fine-tuned using a long chain-of-thought reasoning model and specialized datasets, with a focus on chain-of-thought (CoT) reasoning for problem-solving. This model is optimized for tasks requiring logical reasoning, detailed explanations, and multi-step problem-solving, making it ideal for applications such as instruction-following, text generation, and complex reasoning tasks.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
Key improvements include:
|
| 20 |
|
| 21 |
1. **Enhanced Knowledge and Expertise**: The model demonstrates significantly more knowledge and greatly improved capabilities in coding and mathematics, thanks to specialized expert models in these domains.
|