README.md

metadata

language:
  - ko
  - en
  - zh
  - ja
license: other
library_name: transformers
tags:
  - pytorch
  - TensorBlock
  - GGUF
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
pipeline_tag: text-generation
base_model: beomi/gemma-mling-7b
model-index:
  - name: gemma-mling-7b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 20.29
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 17.63
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 4.15
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 0
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 6.85
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 18.14
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
          name: Open LLM Leaderboard

beomi/gemma-mling-7b - GGUF

This repo contains GGUF format model files for beomi/gemma-mling-7b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Model file specification

Filename	Quant type	File Size	Description
gemma-mling-7b-Q2_K.gguf	Q2_K	3.242 GB	smallest, significant quality loss - not recommended for most purposes
gemma-mling-7b-Q3_K_S.gguf	Q3_K_S	3.709 GB	very small, high quality loss
gemma-mling-7b-Q3_K_M.gguf	Q3_K_M	4.069 GB	very small, high quality loss
gemma-mling-7b-Q3_K_L.gguf	Q3_K_L	4.386 GB	small, substantial quality loss
gemma-mling-7b-Q4_0.gguf	Q4_0	4.668 GB	legacy; small, very high quality loss - prefer using Q3_K_M
gemma-mling-7b-Q4_K_S.gguf	Q4_K_S	4.700 GB	small, greater quality loss
gemma-mling-7b-Q4_K_M.gguf	Q4_K_M	4.964 GB	medium, balanced quality - recommended
gemma-mling-7b-Q5_0.gguf	Q5_0	5.570 GB	legacy; medium, balanced quality - prefer using Q4_K_M
gemma-mling-7b-Q5_K_S.gguf	Q5_K_S	5.570 GB	large, low quality loss - recommended
gemma-mling-7b-Q5_K_M.gguf	Q5_K_M	5.723 GB	large, very low quality loss - recommended
gemma-mling-7b-Q6_K.gguf	Q6_K	6.529 GB	very large, extremely low quality loss
gemma-mling-7b-Q8_0.gguf	Q8_0	8.454 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/gemma-mling-7b-GGUF --include "gemma-mling-7b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/gemma-mling-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'