|
--- |
|
base_model: Rombo-Org/Rombo-LLM-V3.0-Qwen-32b |
|
datasets: |
|
- NovaSky-AI/Sky-T1_data_17k |
|
library_name: transformers |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- llama-cpp |
|
- gguf-my-repo |
|
--- |
|
|
|
# Triangle104/Rombo-LLM-V3.0-Qwen-32b-Q3_K_L-GGUF |
|
This model was converted to GGUF format from [`Rombo-Org/Rombo-LLM-V3.0-Qwen-32b`](https://huggingface.co/Rombo-Org/Rombo-LLM-V3.0-Qwen-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/Rombo-Org/Rombo-LLM-V3.0-Qwen-32b) for more details on the model. |
|
|
|
--- |
|
Rombo-LLM-V3.0-Qwen-32b is a Continued Finetune model on top of the previous V2.5 version using the "NovaSky-AI/Sky-T1_data_17k" dataset. The resulting model was then merged backed into the base model for higher performance as written in the continuous finetuning technique bellow. This model is a good general purpose model, however it excells at coding and math. |
|
|
|
https://docs.google.com/document/d/1OjbjU5AOz4Ftn9xHQrX3oFQGhQ6RDUuXQipnQ9gn6tU/edit?usp=sharing |
|
|
|
--- |
|
## 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/Rombo-LLM-V3.0-Qwen-32b-Q3_K_L-GGUF --hf-file rombo-llm-v3.0-qwen-32b-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo Triangle104/Rombo-LLM-V3.0-Qwen-32b-Q3_K_L-GGUF --hf-file rombo-llm-v3.0-qwen-32b-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/Rombo-LLM-V3.0-Qwen-32b-Q3_K_L-GGUF --hf-file rombo-llm-v3.0-qwen-32b-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo Triangle104/Rombo-LLM-V3.0-Qwen-32b-Q3_K_L-GGUF --hf-file rombo-llm-v3.0-qwen-32b-q3_k_l.gguf -c 2048 |
|
``` |
|
|
