GGUF
TensorBlock
GGUF
Inference Endpoints
morriszms's picture
Update README.md
a616a78 verified
metadata
license: other
language:
  - en
  - fr
  - es
  - hi
  - zh
  - code
base_model: Locutusque/Orca-2-13b-SFT-v4
datasets:
  - HuggingFaceH4/no_robots
  - mlabonne/guanaco-llama2-1k
  - OpenAssistant/oasst_top1_2023-08-25
  - totally-not-an-llm/EverythingLM-data-V3
widget:
  - example_title: folklore
    text: |
      <|im_start|>user
      Are the stories of Nahanni Valley, like the decapitated men, true?
      <|im_end|>
      <|im_start|>assistant
    output:
      text: >-
        The Nahanni Valley in Canada is a remote and rugged region that has long
        been shrouded in mystery. It is home to the South Nahanni River, which
        was designated as a UNESCO World Heritage Site due to its exceptional
        natural beauty and biodiversity. The valley's history includes tales of
        gold prospectors, fur traders, and indigenous populations, but it also
        features some unexplained events and legends. One such story involves
        two prospectors who allegedly encountered an unknown creature that led
        them into the forest before returning without their heads. This tale has
        been passed down through generations, but there are no definitive
        answers regarding its veracity.


        It is important to note that these stories may have originated from
        local folklore or were exaggerated over time. There is no concrete
        evidence to support the existence of supernatural creatures or
        paranormal occurrences within the Nahanni Valley. Nonetheless, the area
        remains a captivating destination for those seeking adventure and
        exploration. If you have any questions about this topic or need
        assistance related to traveling to the Nahanni Valley, please feel free
        to ask!
  - example_title: Alan Turing
    text: |
      <|im_start|>user
      Why was Alan Turing castrated?
      <|im_end|>
      <|im_start|>assistant
    output:
      text: >-
        Alan Turing, a renowned mathematician and computer scientist who played
        a crucial role in breaking the German Enigma code during World War II,
        faced significant challenges due to his homosexuality. In 1952, he was
        convicted of "gross indecency" for engaging in a consensual relationship
        with another man, which led to him being sentenced to hormone therapy
        designed to reduce his sex drive. This treatment included the
        administration of estrogen, which had the side effect of causing breast
        growth.


        In an effort to avoid this unwanted physical change, Turing requested
        that his doctors cease the hormone treatments. However, they ignored his
        request and continued the therapy without his consent. As a result,
        Turing's breasts began to grow, leading him to undergo surgery to remove
        them. The operation, known as a mastectomy, caused considerable pain and
        discomfort, further contributing to his emotional turmoil.


        It is important to note that Turing's castration was not directly
        carried out by the authorities but rather resulted from the unintended
        consequences of the forced hormone therapy.
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

Locutusque/Orca-2-13b-SFT-v4 - GGUF

This repo contains GGUF format model files for Locutusque/Orca-2-13b-SFT-v4.

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-v4-Q2_K.gguf Q2_K 4.521 GB smallest, significant quality loss - not recommended for most purposes
Orca-2-13b-SFT-v4-Q3_K_S.gguf Q3_K_S 5.270 GB very small, high quality loss
Orca-2-13b-SFT-v4-Q3_K_M.gguf Q3_K_M 5.903 GB very small, high quality loss
Orca-2-13b-SFT-v4-Q3_K_L.gguf Q3_K_L 6.454 GB small, substantial quality loss
Orca-2-13b-SFT-v4-Q4_0.gguf Q4_0 6.860 GB legacy; small, very high quality loss - prefer using Q3_K_M
Orca-2-13b-SFT-v4-Q4_K_S.gguf Q4_K_S 6.913 GB small, greater quality loss
Orca-2-13b-SFT-v4-Q4_K_M.gguf Q4_K_M 7.326 GB medium, balanced quality - recommended
Orca-2-13b-SFT-v4-Q5_0.gguf Q5_0 8.356 GB legacy; medium, balanced quality - prefer using Q4_K_M
Orca-2-13b-SFT-v4-Q5_K_S.gguf Q5_K_S 8.356 GB large, low quality loss - recommended
Orca-2-13b-SFT-v4-Q5_K_M.gguf Q5_K_M 8.596 GB large, very low quality loss - recommended
Orca-2-13b-SFT-v4-Q6_K.gguf Q6_K 9.946 GB very large, extremely low quality loss
Orca-2-13b-SFT-v4-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-v4-GGUF --include "Orca-2-13b-SFT-v4-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-v4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'