README.md

metadata

license: unlicense
tags:
  - merge
  - mergekit
  - lazymergekit
  - AI-B/UTENA-7B-UNA-V2
  - AI-B/UTENA-7B-NSFW-V2
  - TensorBlock
  - GGUF
base_model: AI-B/UTENA-7B-V3
model-index:
  - name: UTENA-7B-V3
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 65.96
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 85.7
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.72
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 53.64
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 80.27
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 54.21
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AI-B/UTENA-7B-V3
          name: Open LLM Leaderboard

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

AI-B/UTENA-7B-V3 - GGUF

This repo contains GGUF format model files for AI-B/UTENA-7B-V3.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Run them on the TensorBlock client using your local machine ↗

Prompt template

Model file specification

Filename	Quant type	File Size	Description
UTENA-7B-V3-Q2_K.gguf	Q2_K	2.719 GB	smallest, significant quality loss - not recommended for most purposes
UTENA-7B-V3-Q3_K_S.gguf	Q3_K_S	3.165 GB	very small, high quality loss
UTENA-7B-V3-Q3_K_M.gguf	Q3_K_M	3.519 GB	very small, high quality loss
UTENA-7B-V3-Q3_K_L.gguf	Q3_K_L	3.822 GB	small, substantial quality loss
UTENA-7B-V3-Q4_0.gguf	Q4_0	4.109 GB	legacy; small, very high quality loss - prefer using Q3_K_M
UTENA-7B-V3-Q4_K_S.gguf	Q4_K_S	4.140 GB	small, greater quality loss
UTENA-7B-V3-Q4_K_M.gguf	Q4_K_M	4.368 GB	medium, balanced quality - recommended
UTENA-7B-V3-Q5_0.gguf	Q5_0	4.998 GB	legacy; medium, balanced quality - prefer using Q4_K_M
UTENA-7B-V3-Q5_K_S.gguf	Q5_K_S	4.998 GB	large, low quality loss - recommended
UTENA-7B-V3-Q5_K_M.gguf	Q5_K_M	5.131 GB	large, very low quality loss - recommended
UTENA-7B-V3-Q6_K.gguf	Q6_K	5.942 GB	very large, extremely low quality loss
UTENA-7B-V3-Q8_0.gguf	Q8_0	7.696 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/UTENA-7B-V3-GGUF --include "UTENA-7B-V3-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/UTENA-7B-V3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'