|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- gguf |
|
|
- coding |
|
|
- quantized |
|
|
- Q6_K |
|
|
- olympiccoder |
|
|
- llama.cpp |
|
|
- sychonix |
|
|
inference: false |
|
|
base_model: bartowski/open-r1_OlympicCoder-7B-GGUF |
|
|
model_type: llama |
|
|
quantization_config: |
|
|
quant_method: bitsandbytes |
|
|
load_in_4bit: false |
|
|
load_in_8bit: false |
|
|
weight_dtype: float16 |
|
|
bnb_4bit_quant_type: nf4 |
|
|
--- |
|
|
|
|
|
# 🧠 OlympicCoder 7B Q6 |
|
|
Optimized and quantized version of OlympicCoder 7B designed for algorithmic reasoning, coding challenges, and symbolic inference. |
|
|
|
|
|
... |
|
|
|
|
|
## 🧩 Model Details |
|
|
|
|
|
- **Model Name**: OlympicCoder 7B Q6 |
|
|
- **Quantization**: Q6_K |
|
|
- **Format**: GGUF |
|
|
- **Size**: 6.25 GB |
|
|
- **Architecture**: LLaMA-style 7B |
|
|
- **Compatibility**: `llama.cpp`, `KoboldCpp`, `LM Studio`, `text-generation-webui` |
|
|
|
|
|
--- |
|
|
|
|
|
## 🔧 Recommended Use |
|
|
|
|
|
- 🧮 LeetCode / CodeForces-style problem solving |
|
|
- 💻 Competitive programming and algorithmic reasoning |
|
|
- 🛠️ General-purpose code generation |
|
|
|
|
|
--- |
|
|
|
|
|
## 🚀 How to Use (with `llama.cpp`) |
|
|
|
|
|
```bash |
|
|
./main -m open-r1_OlympicCoder-7B-Q6_K.gguf -p "Write a Python function to solve the 2-sum problem." |
|
|
|
