README.md

metadata

license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
  - TensorBlock
  - GGUF
base_model: allknowingroger/Ph3della5-14B
model-index:
  - name: Ph3della5-14B
    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: 47.99
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3della5-14B
          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: 48.41
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3della5-14B
          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: 14.35
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3della5-14B
          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=allknowingroger/Ph3della5-14B
          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: 14.36
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3della5-14B
          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: 42.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=allknowingroger/Ph3della5-14B
          name: Open LLM Leaderboard

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

allknowingroger/Ph3della5-14B - GGUF

This repo contains GGUF format model files for allknowingroger/Ph3della5-14B.

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

<|user|>
{prompt}<|end|>
<|assistant|>

Model file specification

Filename	Quant type	File Size	Description
Ph3della5-14B-Q2_K.gguf	Q2_K	5.143 GB	smallest, significant quality loss - not recommended for most purposes
Ph3della5-14B-Q3_K_S.gguf	Q3_K_S	6.065 GB	very small, high quality loss
Ph3della5-14B-Q3_K_M.gguf	Q3_K_M	6.923 GB	very small, high quality loss
Ph3della5-14B-Q3_K_L.gguf	Q3_K_L	7.490 GB	small, substantial quality loss
Ph3della5-14B-Q4_0.gguf	Q4_0	7.897 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Ph3della5-14B-Q4_K_S.gguf	Q4_K_S	7.954 GB	small, greater quality loss
Ph3della5-14B-Q4_K_M.gguf	Q4_K_M	8.567 GB	medium, balanced quality - recommended
Ph3della5-14B-Q5_0.gguf	Q5_0	9.622 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Ph3della5-14B-Q5_K_S.gguf	Q5_K_S	9.622 GB	large, low quality loss - recommended
Ph3della5-14B-Q5_K_M.gguf	Q5_K_M	10.074 GB	large, very low quality loss - recommended
Ph3della5-14B-Q6_K.gguf	Q6_K	11.454 GB	very large, extremely low quality loss
Ph3della5-14B-Q8_0.gguf	Q8_0	14.835 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/Ph3della5-14B-GGUF --include "Ph3della5-14B-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/Ph3della5-14B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'