---
license: other
license_name: qwen-research
license_link: https://huggingface.co./huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterate/blob/main/LICENSE
language:
- en
base_model: huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated
pipeline_tag: text-generation
library_name: transformers
tags:
- code
- codeqwen
- chat
- qwen
- qwen-coder
- abliterated
- uncensored
- llama-cpp
- gguf-my-repo
---
# !!TEST!!

## Sage-Restoration_Qwen2.5_IQ4_NL-GGUF  An un-aligned Reasoning model similar to "Replicant" but with more capabilities using Multiple Datasets similar to "THE_KEY" and other private data for furmula table reasoning reinforcement QAT
This model was converted to GGUF format from [`huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated`](https://huggingface.co./huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated) using llama.cpp 
Refer to the [original model card](https://huggingface.co./huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated) for more details on the base model.

For use on many fronts, for *GPT4ALL* Clients use attached System and chat templates in "Jinja-prompt" template file

## 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/Qwen2.5-Coder-3B-Instruct-abliterated-IQ4_NL-GGUF --hf-file qwen2.5-coder-3b-instruct-abliterated-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo fuzzy-mittenz/Qwen2.5-Coder-3B-Instruct-abliterated-IQ4_NL-GGUF --hf-file qwen2.5-coder-3b-instruct-abliterated-iq4_nl-imat.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/Qwen2.5-Coder-3B-Instruct-abliterated-IQ4_NL-GGUF --hf-file qwen2.5-coder-3b-instruct-abliterated-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo fuzzy-mittenz/Qwen2.5-Coder-3B-Instruct-abliterated-IQ4_NL-GGUF --hf-file qwen2.5-coder-3b-instruct-abliterated-iq4_nl-imat.gguf -c 2048
```