|
|
--- |
|
|
base_model: open-thoughts/OpenThinker-32B |
|
|
datasets: |
|
|
- open-thoughts/open-thoughts-114k |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- llama-factory |
|
|
- full |
|
|
- generated_from_trainer |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
model-index: |
|
|
- name: OpenThinker-32B |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
# Triangle104/OpenThinker-32B-Q5_K_S-GGUF |
|
|
This model was converted to GGUF format from [`open-thoughts/OpenThinker-32B`](https://huggingface.co/open-thoughts/OpenThinker-32B) 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/open-thoughts/OpenThinker-32B) for more details on the model. |
|
|
|
|
|
--- |
|
|
This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the OpenThoughts-114k dataset. |
|
|
|
|
|
The dataset is derived by distilling DeepSeek-R1 using the data pipeline available on github. More info about the dataset can be found on the dataset card at OpenThoughts-114k dataset. |
|
|
|
|
|
Intended uses & limitations |
|
|
- |
|
|
Apache 2.0 License |
|
|
|
|
|
Training procedure |
|
|
- |
|
|
We finetune Qwen2.5-32B-Instruct on OpenThoughts-114k for 3 epochs with a 16k context length using LlamaFactory. Our full training configuration is provided in our repository. Training the 32B model on OpenThoughts-114k was done on AWS SageMaker with 8xH100 P5 nodes. On 4 nodes, this took around 90 hours. Meanwhile, for training on OpenThoughts-Unverified-173k, we used 96 nodes of 4xA100 (64 GB per GPU), training took 30 hours, spending 11,520 A100 hours on the Leonardo Supercomputer. |
|
|
|
|
|
--- |
|
|
## 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/OpenThinker-32B-Q5_K_S-GGUF --hf-file openthinker-32b-q5_k_s.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo Triangle104/OpenThinker-32B-Q5_K_S-GGUF --hf-file openthinker-32b-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/OpenThinker-32B-Q5_K_S-GGUF --hf-file openthinker-32b-q5_k_s.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
or |
|
|
``` |
|
|
./llama-server --hf-repo Triangle104/OpenThinker-32B-Q5_K_S-GGUF --hf-file openthinker-32b-q5_k_s.gguf -c 2048 |
|
|
``` |
|
|
|
