Hugging Face's logo

tensorblock
/
Orbita-v0.1-GGUF

GGUF
Turkish
TensorBlock
GGUF
Eval Results
Inference Endpoints
conversational
Model card Files Community
Orbita-v0.1-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
a4614ad verified
preview code
|
raw
history blame contribute delete
5.84 kB
metadata
license: apache-2.0
language:
  - tr
base_model: Orbina/Orbita-v0.1
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: Orbita-v0.1
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge TR
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc
            value: 41.97
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag TR
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc
            value: 48
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU TR
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 49.51
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA TR
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: acc
            value: 50.78
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande TR
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 56.16
            name: accuracy
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k TR
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 50.41
            name: accuracy
TensorBlock

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

Orbina/Orbita-v0.1 - GGUF

This repo contains GGUF format model files for Orbina/Orbita-v0.1.

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

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
Orbita-v0.1-Q2_K.gguf Q2_K 5.506 GB smallest, significant quality loss - not recommended for most purposes
Orbita-v0.1-Q3_K_S.gguf Q3_K_S 6.309 GB very small, high quality loss
Orbita-v0.1-Q3_K_M.gguf Q3_K_M 6.909 GB very small, high quality loss
Orbita-v0.1-Q3_K_L.gguf Q3_K_L 7.302 GB small, substantial quality loss
Orbita-v0.1-Q4_0.gguf Q4_0 7.618 GB legacy; small, very high quality loss - prefer using Q3_K_M
Orbita-v0.1-Q4_K_S.gguf Q4_K_S 7.977 GB small, greater quality loss
Orbita-v0.1-Q4_K_M.gguf Q4_K_M 8.560 GB medium, balanced quality - recommended
Orbita-v0.1-Q5_0.gguf Q5_0 9.176 GB legacy; medium, balanced quality - prefer using Q4_K_M
Orbita-v0.1-Q5_K_S.gguf Q5_K_S 9.339 GB large, low quality loss - recommended
Orbita-v0.1-Q5_K_M.gguf Q5_K_M 9.812 GB large, very low quality loss - recommended
Orbita-v0.1-Q6_K.gguf Q6_K 11.465 GB very large, extremely low quality loss
Orbita-v0.1-Q8_0.gguf Q8_0 14.027 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/Orbita-v0.1-GGUF --include "Orbita-v0.1-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/Orbita-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'