|
|
--- |
|
|
library_name: transformers |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- 32 k context |
|
|
- reasoning |
|
|
- thinking |
|
|
- qwen3 |
|
|
- 4 experts activated |
|
|
- double speed |
|
|
- 128 experts |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
base_model: DavidAU/Qwen3-30B-A1.5B-High-Speed |
|
|
--- |
|
|
|
|
|
# Triangle104/Qwen3-30B-A1.5B-High-Speed-Q3_K_L-GGUF |
|
|
This model was converted to GGUF format from [`DavidAU/Qwen3-30B-A1.5B-High-Speed`](https://huggingface.co/DavidAU/Qwen3-30B-A1.5B-High-Speed) 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/DavidAU/Qwen3-30B-A1.5B-High-Speed) for more details on the model. |
|
|
|
|
|
--- |
|
|
This is a simple "finetune" of the Qwen's "Qwen 30B-A3B" (MOE) model, |
|
|
setting the experts in use from 8 to 4 (out of 128 experts). |
|
|
|
|
|
|
|
|
This method close to doubles the speed of the model and uses 1.5B (of |
|
|
30B) parameters instead of 3B (of 30B) parameters. Depending on the |
|
|
application you may want to |
|
|
use the regular model ("30B-A3B"), and use this model for simpler use |
|
|
case(s) although I did not notice any loss of function during |
|
|
routine (but not extensive) testing. |
|
|
|
|
|
--- |
|
|
## 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 Triangle104/Qwen3-30B-A1.5B-High-Speed-Q3_K_L-GGUF --hf-file qwen3-30b-a1.5b-high-speed-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo Triangle104/Qwen3-30B-A1.5B-High-Speed-Q3_K_L-GGUF --hf-file qwen3-30b-a1.5b-high-speed-q3_k_l.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 Triangle104/Qwen3-30B-A1.5B-High-Speed-Q3_K_L-GGUF --hf-file qwen3-30b-a1.5b-high-speed-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
or |
|
|
``` |
|
|
./llama-server --hf-repo Triangle104/Qwen3-30B-A1.5B-High-Speed-Q3_K_L-GGUF --hf-file qwen3-30b-a1.5b-high-speed-q3_k_l.gguf -c 2048 |
|
|
``` |
|
|
|
