|
--- |
|
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. |
|
|
|
## 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 |
|
``` |
|
|
