risangpanggalih's picture
Update README.md
85a5285 verified
metadata
base_model: risangpanggalih/Bokap-Betawi-v0-Qwen2.5-7B-fp16
library_name: transformers
tags:
  - unsloth
  - trl
  - sft
  - llama-cpp
  - gguf-my-repo
  - qwen2.5
datasets:
  - risangpanggalih/betawi-v0

Betawi Language Model: Bokap Betawi-7B

Bokap Betawi

Bokap Betawi is a language model fine-tuned from Qwen 2.5 7B on 1,000 instruction-output pairs synthetic Betawi language dataset generated using GPT-4o. This model is specifically made to enhance the performance of tasks in bahasa Betawi.

Version Alpha

This model was converted to GGUF format from risangpanggalih/Bokap-Betawi-v0-Qwen2.5-7B-fp16 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. See here for another version:

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo risangpanggalih/Bokap-Betawi-v0-Qwen2.5-7B-fp16-Q8_0-GGUF --hf-file bokap-betawi-v0-qwen2.5-7b-fp16-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo risangpanggalih/Bokap-Betawi-v0-Qwen2.5-7B-fp16-Q8_0-GGUF --hf-file bokap-betawi-v0-qwen2.5-7b-fp16-q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps 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 risangpanggalih/Bokap-Betawi-v0-Qwen2.5-7B-fp16-Q8_0-GGUF --hf-file bokap-betawi-v0-qwen2.5-7b-fp16-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo risangpanggalih/Bokap-Betawi-v0-Qwen2.5-7B-fp16-Q8_0-GGUF --hf-file bokap-betawi-v0-qwen2.5-7b-fp16-q8_0.gguf -c 2048

Description

  • Developed by: Risang Panggalih
  • Finetuned from model: Qwen 2.5 7B