|
--- |
|
license: apache-2.0 |
|
tags: |
|
- llama-cpp |
|
- gguf-my-repo |
|
base_model: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview |
|
--- |
|
|
|
# Triangle104/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview-Q3_K_L-GGUF |
|
This model was converted to GGUF format from [`FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview`](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview) 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/FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview) for more details on the model. |
|
|
|
--- |
|
FuseO1-Preview is our initial endeavor to enhance the System-II reasoning capabilities of large language models (LLMs) through innovative model fusion techniques. By employing our advanced SCE merging methodologies, we integrate multiple open-source o1-like LLMs into a unified model. Our goal is to incorporate the distinct knowledge and strengths from different reasoning LLMs into a single, unified model with strong System-II reasoning abilities, particularly in mathematics, coding, and science domains. |
|
|
|
|
|
To achieve this, we conduct two types of model merging: |
|
|
|
Long-Long Reasoning Merging: This approach involves model fusion across LLMs that utilize long-CoT reasoning, with the goal of enhancing long-CoT reasoning capabilities. The resulted FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview achieves a Pass@1 accuracy of 74.0 on AIME24, demonstrating significant performance improvements compared to the OpenAI o1-preview (44.6) and OpenAI o1-mini (63.4), even approaching OpenAI o1 (79.2). |
|
Long-Short Reasoning Merging: This approach involves model fusion between long-CoT and short-CoT LLMs, aiming to improve reasoning capabilities in both long and short reasoning processes. The resulted FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Instruct-32B-Preview and FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview is capable of utilizing both long and short reasoning processes and demonstrates relatively strong performance in long reasoning tasks. |
|
|
|
--- |
|
## 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/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview-Q3_K_L-GGUF --hf-file fuseo1-deepseekr1-qwq-skyt1-flash-32b-preview-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo Triangle104/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview-Q3_K_L-GGUF --hf-file fuseo1-deepseekr1-qwq-skyt1-flash-32b-preview-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/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview-Q3_K_L-GGUF --hf-file fuseo1-deepseekr1-qwq-skyt1-flash-32b-preview-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo Triangle104/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview-Q3_K_L-GGUF --hf-file fuseo1-deepseekr1-qwq-skyt1-flash-32b-preview-q3_k_l.gguf -c 2048 |
|
``` |
|
|
