|
|
--- |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- open-r1/Mixture-of-Thoughts |
|
|
- nvidia/OpenCodeReasoning |
|
|
language: |
|
|
- en |
|
|
base_model: prithivMLmods/Lacaille-MoT-4B-Supreme2 |
|
|
pipeline_tag: text-generation |
|
|
library_name: transformers |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- math |
|
|
- science |
|
|
- moe |
|
|
- code |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
--- |
|
|
|
|
|
# Triangle104/Lacaille-MoT-4B-Supreme2-Q5_K_S-GGUF |
|
|
This model was converted to GGUF format from [`prithivMLmods/Lacaille-MoT-4B-Supreme2`](https://huggingface.co/prithivMLmods/Lacaille-MoT-4B-Supreme2) 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/prithivMLmods/Lacaille-MoT-4B-Supreme2) for more details on the model. |
|
|
|
|
|
--- |
|
|
Lacaille-MoT-4B-Supreme2 is a high-efficiency, multi-domain model fine-tuned on Qwen3-4B using the Mixture of Thoughts (MoT) dataset enhanced with code, math, science expert clusters and an extended open code reasoning dataset. |
|
|
This model blends symbolic precision, scientific logic, and structured |
|
|
output fluency—making it an ideal tool for developers, educators, and |
|
|
researchers seeking advanced reasoning under constrained compute. |
|
|
|
|
|
--- |
|
|
## 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/Lacaille-MoT-4B-Supreme2-Q5_K_S-GGUF --hf-file lacaille-mot-4b-supreme2-q5_k_s.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo Triangle104/Lacaille-MoT-4B-Supreme2-Q5_K_S-GGUF --hf-file lacaille-mot-4b-supreme2-q5_k_s.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/Lacaille-MoT-4B-Supreme2-Q5_K_S-GGUF --hf-file lacaille-mot-4b-supreme2-q5_k_s.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
or |
|
|
``` |
|
|
./llama-server --hf-repo Triangle104/Lacaille-MoT-4B-Supreme2-Q5_K_S-GGUF --hf-file lacaille-mot-4b-supreme2-q5_k_s.gguf -c 2048 |
|
|
``` |
|
|
|
