README.md

metadata

license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
datasets:
  - Magpie-Align/Magpie-Qwen2.5-Pro-1M-v0.1
base_model: fblgit/cybertron-v4-qw7B-MGS
library_name: transformers
tags:
  - generated_from_trainer
  - TensorBlock
  - GGUF
language:
  - en
model-index:
  - name: cybertron-v4-qw7B-MGS
    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: 62.64
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
          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: 37.04
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
          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: 27.72
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
          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: 8.05
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
          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: 13.2
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
          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: 38.59
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/cybertron-v4-qw7B-MGS
          name: Open LLM Leaderboard

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

fblgit/cybertron-v4-qw7B-MGS - GGUF

This repo contains GGUF format model files for fblgit/cybertron-v4-qw7B-MGS.

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

Run them on the TensorBlock client using your local machine ↗

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
cybertron-v4-qw7B-MGS-Q2_K.gguf	Q2_K	3.016 GB	smallest, significant quality loss - not recommended for most purposes
cybertron-v4-qw7B-MGS-Q3_K_S.gguf	Q3_K_S	3.492 GB	very small, high quality loss
cybertron-v4-qw7B-MGS-Q3_K_M.gguf	Q3_K_M	3.808 GB	very small, high quality loss
cybertron-v4-qw7B-MGS-Q3_K_L.gguf	Q3_K_L	4.088 GB	small, substantial quality loss
cybertron-v4-qw7B-MGS-Q4_0.gguf	Q4_0	4.431 GB	legacy; small, very high quality loss - prefer using Q3_K_M
cybertron-v4-qw7B-MGS-Q4_K_S.gguf	Q4_K_S	4.458 GB	small, greater quality loss
cybertron-v4-qw7B-MGS-Q4_K_M.gguf	Q4_K_M	4.683 GB	medium, balanced quality - recommended
cybertron-v4-qw7B-MGS-Q5_0.gguf	Q5_0	5.315 GB	legacy; medium, balanced quality - prefer using Q4_K_M
cybertron-v4-qw7B-MGS-Q5_K_S.gguf	Q5_K_S	5.315 GB	large, low quality loss - recommended
cybertron-v4-qw7B-MGS-Q5_K_M.gguf	Q5_K_M	5.445 GB	large, very low quality loss - recommended
cybertron-v4-qw7B-MGS-Q6_K.gguf	Q6_K	6.254 GB	very large, extremely low quality loss
cybertron-v4-qw7B-MGS-Q8_0.gguf	Q8_0	8.099 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/cybertron-v4-qw7B-MGS-GGUF --include "cybertron-v4-qw7B-MGS-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/cybertron-v4-qw7B-MGS-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'