README.md

---
language:
- en
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
base_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- teknium/openhermes
---

# v8karlo/TinyDolphin-2.8.1-1.1b-Q4_K_M-GGUF

UNCENSORED model.
In order to make your GGUF file type go to original Tiny Dolphin repo.
https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b?text=My+name+is+Teven+and+I+am+a+20-year-old+college+student+from+the+University+of+Kansas.+I+have+a+passion  .
Copy name of the model TinyDolphin-2.8-1.1b.
Go to Convert-to-GGUF repo https://huggingface.co/spaces/ggml-org/gguf-my-repo and paste model name into Hub Model ID field, choose Quantization Method and press Submit button.

This model was converted to GGUF format from [`cognitivecomputations/TinyDolphin-2.8.1-1.1b`](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b) for more details on the model.

Convert Safetensors to GGUF  .
https://huggingface.co/spaces/ggml-org/gguf-my-repo  .
![image/png](https://cdn-uploads.huggingface.co/production/uploads/662c3116277765660783ca6d/NhfH9cw1jZ77FeQV6EFT9.png)



## 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 --hf-repo v8karlo/TinyDolphin-2.8.1-1.1b-Q4_K_M-GGUF --hf-file tinydolphin-2.8.1-1.1b-q4_k_m.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo v8karlo/TinyDolphin-2.8.1-1.1b-Q4_K_M-GGUF --hf-file tinydolphin-2.8.1-1.1b-q4_k_m.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.
```
./main --hf-repo v8karlo/TinyDolphin-2.8.1-1.1b-Q4_K_M-GGUF --hf-file tinydolphin-2.8.1-1.1b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or 
```
./server --hf-repo v8karlo/TinyDolphin-2.8.1-1.1b-Q4_K_M-GGUF --hf-file tinydolphin-2.8.1-1.1b-q4_k_m.gguf -c 2048
```