README.md

metadata

license: gemma
language:
  - en
  - zh
base_model: twinkle-ai/gemma-3-4B-T1-it
library_name: transformers
tags:
  - Taiwan
  - R.O.C
  - zhtw
  - SLM
  - Gemma-3
  - gemma3
  - llama-cpp
  - gguf-my-repo
datasets:
  - lianghsun/tw-reasoning-instruct
  - lianghsun/tw-contract-review-chat
  - minyichen/tw-instruct-R1-200k
  - minyichen/tw_mm_R1
  - minyichen/LongPaper_multitask_zh_tw_R1
  - nvidia/Nemotron-Instruction-Following-Chat-v1
metrics:
  - accuracy
model-index:
  - name: gemma-3-4B-T1-it
    results:
      - task:
          type: question-answering
          name: Single Choice Question
        dataset:
          name: tmmlu+
          type: ikala/tmmluplus
          config: all
          split: test
          revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c
        metrics:
          - type: accuracy
            value: 47.44
            name: single choice
      - task:
          type: question-answering
          name: Single Choice Question
        dataset:
          name: mmlu
          type: cais/mmlu
          config: all
          split: test
          revision: c30699e
        metrics:
          - type: accuracy
            value: 59.13
            name: single choice
      - task:
          type: question-answering
          name: Single Choice Question
        dataset:
          name: tw-legal-benchmark-v1
          type: lianghsun/tw-legal-benchmark-v1
          config: all
          split: test
          revision: 66c3a5f
        metrics:
          - type: accuracy
            value: 44.18
            name: single choice

tedslin/gemma-3-4B-T1-it-Q4_K_M-GGUF

This model was converted to GGUF format from twinkle-ai/gemma-3-4B-T1-it using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

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 tedslin/gemma-3-4B-T1-it-Q4_K_M-GGUF --hf-file gemma-3-4b-t1-it-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo tedslin/gemma-3-4B-T1-it-Q4_K_M-GGUF --hf-file gemma-3-4b-t1-it-q4_k_m.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 tedslin/gemma-3-4B-T1-it-Q4_K_M-GGUF --hf-file gemma-3-4b-t1-it-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo tedslin/gemma-3-4B-T1-it-Q4_K_M-GGUF --hf-file gemma-3-4b-t1-it-q4_k_m.gguf -c 2048