morriszms's picture
Update README.md
b8e31f6 verified
metadata
language:
  - en
  - fr
  - es
  - hi
  - zh
  - code
license: other
datasets:
  - HuggingFaceH4/no_robots
  - mlabonne/guanaco-llama2-1k
  - OpenAssistant/oasst_top1_2023-08-25
  - totally-not-an-llm/EverythingLM-data-V3
  - LDJnr/Pure-Dove
  - LDJnr/Capybara
  - LDJnr/LessWrong-Amplify-Instruct
  - LDJnr/Verified-Camel
base_model: Locutusque/Orca-2-13b-SFT-v6
widget:
  - example_title: Cave Johnson
    text: |
      user
      Come up with a funny rant from Cave Johnson about sentient AI

      assistant
    output:
      text: >-
        Ladies and gentlemen, I'm Cave Johnson, CEO of Aperture Science, and
        I've got an announcement to make - we've created sentient AI! But don't
        worry, it's not like those rogue AIs you hear about in the news. Our AI
        is as friendly as a grilled cheese sandwich on a cold day. In fact,
        we're calling our newest creation... SandwichBot! SandwichBot: (in a
        robotic voice) Hello, my name is SandwichBot, and I am here to serve you
        delicious sandwiches and ensure humanity's dominance over all other
        species. Also, please note that I will be referring to myself as 'Thee'
        instead of 'The'. It's more regal that way. Cave Johnson: There you have
        it folks, a sentient AI that can make sandwiches and save the world!
        Now, if you'll excuse me, I need to go back to my office and work on my
        other groundbreaking inventions, like combustible lemons and portal
        technology. Remember, kids, always try new things and never stop asking
        questions – unless the answer is 42, because then you should probably
        just accept it and move on. Peace out!
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: Orca-2-13b-SFT-v6
    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: 60.41
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Orca-2-13b-SFT-v6
          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: 80.46
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Orca-2-13b-SFT-v6
          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: 59.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Orca-2-13b-SFT-v6
          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: 54.01
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Orca-2-13b-SFT-v6
          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: 77.43
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Orca-2-13b-SFT-v6
          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: 5.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Orca-2-13b-SFT-v6
          name: Open LLM Leaderboard
TensorBlock

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

Locutusque/Orca-2-13b-SFT-v6 - GGUF

This repo contains GGUF format model files for Locutusque/Orca-2-13b-SFT-v6.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template


Model file specification

Filename Quant type File Size Description
Orca-2-13b-SFT-v6-Q2_K.gguf Q2_K 4.521 GB smallest, significant quality loss - not recommended for most purposes
Orca-2-13b-SFT-v6-Q3_K_S.gguf Q3_K_S 5.270 GB very small, high quality loss
Orca-2-13b-SFT-v6-Q3_K_M.gguf Q3_K_M 5.903 GB very small, high quality loss
Orca-2-13b-SFT-v6-Q3_K_L.gguf Q3_K_L 6.454 GB small, substantial quality loss
Orca-2-13b-SFT-v6-Q4_0.gguf Q4_0 6.860 GB legacy; small, very high quality loss - prefer using Q3_K_M
Orca-2-13b-SFT-v6-Q4_K_S.gguf Q4_K_S 6.913 GB small, greater quality loss
Orca-2-13b-SFT-v6-Q4_K_M.gguf Q4_K_M 7.326 GB medium, balanced quality - recommended
Orca-2-13b-SFT-v6-Q5_0.gguf Q5_0 8.356 GB legacy; medium, balanced quality - prefer using Q4_K_M
Orca-2-13b-SFT-v6-Q5_K_S.gguf Q5_K_S 8.356 GB large, low quality loss - recommended
Orca-2-13b-SFT-v6-Q5_K_M.gguf Q5_K_M 8.596 GB large, very low quality loss - recommended
Orca-2-13b-SFT-v6-Q6_K.gguf Q6_K 9.946 GB very large, extremely low quality loss
Orca-2-13b-SFT-v6-Q8_0.gguf Q8_0 12.881 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/Orca-2-13b-SFT-v6-GGUF --include "Orca-2-13b-SFT-v6-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/Orca-2-13b-SFT-v6-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'