|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
metrics: |
|
- RAGAS |
|
pipeline_tag: question-answering |
|
base_model: |
|
- Qwen/Qwen2.5-3B-Instruct |
|
--- |
|
|
|
# Sidemen_Intellihack_QwenModel |
|
|
|
This model is a fine-tuned version of [Qwen 2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) tailored for technical question-answering tasks in the domain of AI research. |
|
|
|
## Model Details |
|
|
|
- **Base Model:** [Qwen 2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) |
|
- **Architecture:** Transformer-based language model with 3 billion parameters. |
|
- **Quantization:** 4-bit GGUF format using the `q4_k_m` method for efficient inference. |
|
|
