---
license: mit
library_name: transformers
datasets:
- AI-MO/NuminaMath-CoT
- KbsdJames/Omni-MATH
- RUC-AIBOX/STILL-3-Preview-RL-Data
- hendrycks/competition_math
language:
- en
base_model: agentica-org/DeepScaleR-1.5B-Preview
tags:
- llama-cpp
---

# IntelligentEstate/Tiny_Rabbit-R1-Q8_0-GGUF

## This is a *Complex* reasoning model, it has a unique ability to reason through the incorperation of *NEW* information. With this model you can now choose how to introduce the new information.
![white rabbit.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/00opTsiF4DDl8x8qttVSa.png)
Reasoning models operate within their respective Knowledge base. This is helpfull in contextualizing new complex information or introduction of new material. It is rare they exceed the reasoning knowledge base alone. This model excells when re-expressing information from the web or a RAG database. For quick use in Swarm bases this is a great little model when given proper context and instructions. Generally though it increases the knowledge base from -20% thru +10% so verify your application uasage through testing before application. The 1.5B model this is based on has reinforced mathmatical context, increasing the tool use and suprisingly it's short form writing. Enjoy and please leave feedback.
This model was converted to GGUF format from [`agentica-org/DeepScaleR-1.5B-Preview`](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview) using llama.cpp 
Refer to the [original model card](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo fuzzy-mittenz/DeepScaleR-1.5B-Preview-Q8_0-GGUF --hf-file deepscaler-1.5b-preview-q8_0.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo fuzzy-mittenz/DeepScaleR-1.5B-Preview-Q8_0-GGUF --hf-file deepscaler-1.5b-preview-q8_0.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo fuzzy-mittenz/DeepScaleR-1.5B-Preview-Q8_0-GGUF --hf-file deepscaler-1.5b-preview-q8_0.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo fuzzy-mittenz/DeepScaleR-1.5B-Preview-Q8_0-GGUF --hf-file deepscaler-1.5b-preview-q8_0.gguf -c 2048
```