README.md

metadata

language:
  - en
license: cc-by-nc-sa-4.0
library_name: transformers
datasets:
  - psmathur/alpaca_orca
  - psmathur/dolly-v2_orca
  - psmathur/WizardLM_Orca
pipeline_tag: text-generation
tags:
  - TensorBlock
  - GGUF
base_model: pankajmathur/orca_mini_3b
model-index:
  - name: orca_mini_3b
    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: 41.55
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
          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: 61.52
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
          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: 26.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
          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: 42.42
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
          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: 61.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
          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: 0.08
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
          name: Open LLM Leaderboard

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

pankajmathur/orca_mini_3b - GGUF

This repo contains GGUF format model files for pankajmathur/orca_mini_3b.

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_mini_3b-Q2_K.gguf	Q2_K	1.844 GB	smallest, significant quality loss - not recommended for most purposes
orca_mini_3b-Q3_K_S.gguf	Q3_K_S	1.844 GB	very small, high quality loss
orca_mini_3b-Q3_K_M.gguf	Q3_K_M	1.992 GB	very small, high quality loss
orca_mini_3b-Q3_K_L.gguf	Q3_K_L	2.062 GB	small, substantial quality loss
orca_mini_3b-Q4_0.gguf	Q4_0	1.844 GB	legacy; small, very high quality loss - prefer using Q3_K_M
orca_mini_3b-Q4_K_S.gguf	Q4_K_S	2.238 GB	small, greater quality loss
orca_mini_3b-Q4_K_M.gguf	Q4_K_M	2.403 GB	medium, balanced quality - recommended
orca_mini_3b-Q5_0.gguf	Q5_0	2.231 GB	legacy; medium, balanced quality - prefer using Q4_K_M
orca_mini_3b-Q5_K_S.gguf	Q5_K_S	2.424 GB	large, low quality loss - recommended
orca_mini_3b-Q5_K_M.gguf	Q5_K_M	2.568 GB	large, very low quality loss - recommended
orca_mini_3b-Q6_K.gguf	Q6_K	3.392 GB	very large, extremely low quality loss
orca_mini_3b-Q8_0.gguf	Q8_0	3.392 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_mini_3b-GGUF --include "orca_mini_3b-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_mini_3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'