README.md · tensorblock/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-GGUF at main

metadata

language:
  - en
  - de
license: apache-2.0
tags:
  - chat
  - TensorBlock
  - GGUF
base_model: Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
model-index:
  - name: Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
    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: 82.92
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
          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: 48.05
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
          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: 0
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
          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: 12.3
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
          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: 13.15
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
          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: 44.65
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
          name: Open LLM Leaderboard

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

Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4 - GGUF

This repo contains GGUF format model files for Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4.

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
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q2_K.gguf	Q2_K	5.770 GB	smallest, significant quality loss - not recommended for most purposes
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q3_K_S.gguf	Q3_K_S	6.660 GB	very small, high quality loss
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q3_K_M.gguf	Q3_K_M	7.339 GB	very small, high quality loss
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q3_K_L.gguf	Q3_K_L	7.925 GB	small, substantial quality loss
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q4_0.gguf	Q4_0	8.518 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q4_K_S.gguf	Q4_K_S	8.573 GB	small, greater quality loss
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q4_K_M.gguf	Q4_K_M	8.988 GB	medium, balanced quality - recommended
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q5_0.gguf	Q5_0	10.267 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q5_K_S.gguf	Q5_K_S	10.267 GB	large, low quality loss - recommended
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q5_K_M.gguf	Q5_K_M	10.509 GB	large, very low quality loss - recommended
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q6_K.gguf	Q6_K	12.125 GB	very large, extremely low quality loss
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-Q8_0.gguf	Q8_0	15.702 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/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-GGUF --include "Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-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/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'