README.md

metadata

language:
  - en
  - fr
  - es
  - ru
  - zh
  - ja
  - fa
  - code
license: mit
library_name: transformers
tags:
  - fluently-lm
  - fluently
  - prinum
  - instruct
  - trained
  - math
  - roleplay
  - reasoning
  - axolotl
  - unsloth
  - argilla
  - qwen2
  - TensorBlock
  - GGUF
datasets:
  - fluently-sets/ultraset
  - fluently-sets/ultrathink
  - fluently-sets/reasoning-1-1k
  - fluently-sets/MATH-500-Overall
inference: true
pipeline_tag: text-generation
base_model: fluently-lm/FluentlyLM-Prinum
model-index:
  - name: FluentlyLM-Prinum
    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: 80.9
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
          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: 59.48
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
          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: 54
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
          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: 18.23
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
          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: 17.26
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
          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: 53.42
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
          name: Open LLM Leaderboard

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

fluently-lm/FluentlyLM-Prinum - GGUF

This repo contains GGUF format model files for fluently-lm/FluentlyLM-Prinum.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

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
FluentlyLM-Prinum-Q2_K.gguf	Q2_K	12.313 GB	smallest, significant quality loss - not recommended for most purposes
FluentlyLM-Prinum-Q3_K_S.gguf	Q3_K_S	14.392 GB	very small, high quality loss
FluentlyLM-Prinum-Q3_K_M.gguf	Q3_K_M	15.935 GB	very small, high quality loss
FluentlyLM-Prinum-Q3_K_L.gguf	Q3_K_L	17.247 GB	small, substantial quality loss
FluentlyLM-Prinum-Q4_0.gguf	Q4_0	18.640 GB	legacy; small, very high quality loss - prefer using Q3_K_M
FluentlyLM-Prinum-Q4_K_S.gguf	Q4_K_S	18.784 GB	small, greater quality loss
FluentlyLM-Prinum-Q4_K_M.gguf	Q4_K_M	19.851 GB	medium, balanced quality - recommended
FluentlyLM-Prinum-Q5_0.gguf	Q5_0	22.638 GB	legacy; medium, balanced quality - prefer using Q4_K_M
FluentlyLM-Prinum-Q5_K_S.gguf	Q5_K_S	22.638 GB	large, low quality loss - recommended
FluentlyLM-Prinum-Q5_K_M.gguf	Q5_K_M	23.262 GB	large, very low quality loss - recommended
FluentlyLM-Prinum-Q6_K.gguf	Q6_K	26.886 GB	very large, extremely low quality loss
FluentlyLM-Prinum-Q8_0.gguf	Q8_0	34.821 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/FluentlyLM-Prinum-GGUF --include "FluentlyLM-Prinum-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/FluentlyLM-Prinum-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'