|
--- |
|
license: apache-2.0 |
|
tags: |
|
- llama-cpp |
|
- gguf-my-repo |
|
base_model: internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B |
|
--- |
|
|
|
# Triangle104/OREAL-DeepSeek-R1-Distill-Qwen-7B-Q4_K_S-GGUF |
|
This model was converted to GGUF format from [`internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B`](https://huggingface.co/internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B) 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/internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B) for more details on the model. |
|
|
|
--- |
|
Introduction |
|
|
|
|
|
|
|
|
|
We introduce OREAL-7B and OREAL-32B, a mathematical reasoning model series trained using Outcome REwArd-based reinforcement Learning, a novel RL framework designed for tasks where only binary outcome rewards are available. |
|
|
|
|
|
With OREAL, a 7B model achieves 94.0 pass@1 accuracy on MATH-500, matching the performance of previous 32B models. OREAL-32B further surpasses previous distillation-trained 32B models, reaching 95.0 pass@1 accuracy on MATH-500. |
|
|
|
|
|
|
|
|
|
|
|
Our method leverages best-of-N (BoN) sampling for behavior cloning |
|
and reshapes negative sample rewards to ensure gradient consistency. |
|
Also, to address the challenge of sparse rewards in long |
|
chain-of-thought reasoning, we incorporate an on-policy token-level |
|
reward model that identifies key tokens in reasoning trajectories for |
|
importance sampling. For more details, please refer to our paper. |
|
|
|
--- |
|
## 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/OREAL-DeepSeek-R1-Distill-Qwen-7B-Q4_K_S-GGUF --hf-file oreal-deepseek-r1-distill-qwen-7b-q4_k_s.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo Triangle104/OREAL-DeepSeek-R1-Distill-Qwen-7B-Q4_K_S-GGUF --hf-file oreal-deepseek-r1-distill-qwen-7b-q4_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/OREAL-DeepSeek-R1-Distill-Qwen-7B-Q4_K_S-GGUF --hf-file oreal-deepseek-r1-distill-qwen-7b-q4_k_s.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo Triangle104/OREAL-DeepSeek-R1-Distill-Qwen-7B-Q4_K_S-GGUF --hf-file oreal-deepseek-r1-distill-qwen-7b-q4_k_s.gguf -c 2048 |
|
``` |
|
|
