Update README.md
Browse files
README.md
CHANGED
|
@@ -7,43 +7,51 @@ tags:
|
|
| 7 |
- Q6_K
|
| 8 |
- olympiccoder
|
| 9 |
- llama.cpp
|
| 10 |
-
|
| 11 |
inference: false
|
| 12 |
base_model: bartowski/open-r1_OlympicCoder-7B-GGUF
|
| 13 |
-
model_type: llama
|
| 14 |
-
quantization_config:
|
| 15 |
-
quant_method: bitsandbytes
|
| 16 |
-
load_in_4bit: false
|
| 17 |
-
load_in_8bit: false
|
| 18 |
-
weight_dtype: float16
|
| 19 |
-
bnb_4bit_quant_type: nf4
|
| 20 |
---
|
| 21 |
|
| 22 |
-
#
|
| 23 |
-
|
|
|
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
-
##
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
|
| 36 |
---
|
| 37 |
|
| 38 |
-
##
|
| 39 |
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
|
| 44 |
---
|
| 45 |
|
| 46 |
-
## ๐ How to
|
| 47 |
|
| 48 |
```bash
|
| 49 |
-
./main -m open-r1_OlympicCoder-7B-Q6_K.gguf -p "Write a
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- Q6_K
|
| 8 |
- olympiccoder
|
| 9 |
- llama.cpp
|
| 10 |
+
model_type: llama
|
| 11 |
inference: false
|
| 12 |
base_model: bartowski/open-r1_OlympicCoder-7B-GGUF
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# ๐ง OlympicCoder 7B Q6
|
| 16 |
+
|
| 17 |
+
Optimized and quantized version of OlympicCoder 7B designed for algorithmic reasoning, competitive programming, and symbolic inference.
|
| 18 |
|
| 19 |
+
---
|
| 20 |
|
| 21 |
+
## ๐ Model Details
|
| 22 |
|
| 23 |
+
* **Model Name**: OlympicCoder 7B Q6
|
| 24 |
+
* **Quantization**: Q6\_K
|
| 25 |
+
* **Format**: GGUF
|
| 26 |
+
* **Size**: 6.25 GB
|
| 27 |
+
* **Architecture**: LLaMA-style 7B
|
| 28 |
+
* **Base Model**: [open-r1\_OlympicCoder-7B-GGUF](https://huggingface.co/bartowski/open-r1_OlympicCoder-7B-GGUF)
|
| 29 |
|
| 30 |
---
|
| 31 |
|
| 32 |
+
## ๐ ๏ธ Use Cases
|
| 33 |
|
| 34 |
+
* โ๏ธ Competitive programming and Codeforces-style tasks
|
| 35 |
+
* ๐ Symbolic reasoning and algorithmic inference
|
| 36 |
+
* ๐ป Code generation and technical prompts
|
| 37 |
|
| 38 |
---
|
| 39 |
|
| 40 |
+
## ๐ How to Run (with llama.cpp)
|
| 41 |
|
| 42 |
```bash
|
| 43 |
+
./main -m open-r1_OlympicCoder-7B-Q6_K.gguf -p "Write a function that checks if a number is prime."
|
| 44 |
+
```
|
| 45 |
+
|
| 46 |
+
Other tools:
|
| 47 |
+
|
| 48 |
+
* **LM Studio**: Import `.gguf` and chat directly
|
| 49 |
+
* **KoboldCpp** / **text-generation-webui**: Load as GGUF model
|
| 50 |
+
|
| 51 |
+
---
|
| 52 |
+
|
| 53 |
+
## ๐ License
|
| 54 |
+
|
| 55 |
+
Apache 2.0 โ free for commercial and research use.
|
| 56 |
+
|
| 57 |
+
---
|