README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
  - TensorBlock
  - GGUF
base_model: CultriX/Qwen2.5-14B-Wernicke
license: apache-2.0
language:
  - en
metrics:
  - accuracy
pipeline_tag: text-generation
model-index:
  - name: Qwen2.5-14B-Wernicke
    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: 52.35
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
          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: 50.64
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
          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: 30.06
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
          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: 19.13
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
          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: 18.25
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
          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: 49.15
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CultriX/Qwen2.5-14B-Wernicke
          name: Open LLM Leaderboard

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

CultriX/Qwen2.5-14B-Wernicke - GGUF

This repo contains GGUF format model files for CultriX/Qwen2.5-14B-Wernicke.

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