README.md

metadata

license: mit
datasets:
  - Open-Orca/SlimOrca-Dedup
  - migtissera/Synthia-v1.3
  - LDJnr/Verified-Camel
  - LDJnr/Pure-Dove
  - LDJnr/Capybara
  - meta-math/MetaMathQA
  - Intel/orca_dpo_pairs
  - argilla/ultrafeedback-binarized-preferences-cleaned
widget:
  - example_title: Example interaction
    text: Why is the sky blue?
inference:
  parameters:
    do_sample: true
    temperature: 0.1
tags:
  - TensorBlock
  - GGUF
base_model: rhysjones/phi-2-orange-v2
model-index:
  - name: phi-2-orange-v2
    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: 61.86
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
          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: 76.32
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
          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: 55.72
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
          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: 54.84
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
          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: 75.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
          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: 57.62
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rhysjones/phi-2-orange-v2
          name: Open LLM Leaderboard

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

rhysjones/phi-2-orange-v2 - GGUF

This repo contains GGUF format model files for rhysjones/phi-2-orange-v2.

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

<|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
phi-2-orange-v2-Q2_K.gguf	Q2_K	1.110 GB	smallest, significant quality loss - not recommended for most purposes
phi-2-orange-v2-Q3_K_S.gguf	Q3_K_S	1.251 GB	very small, high quality loss
phi-2-orange-v2-Q3_K_M.gguf	Q3_K_M	1.426 GB	very small, high quality loss
phi-2-orange-v2-Q3_K_L.gguf	Q3_K_L	1.575 GB	small, substantial quality loss
phi-2-orange-v2-Q4_0.gguf	Q4_0	1.602 GB	legacy; small, very high quality loss - prefer using Q3_K_M
phi-2-orange-v2-Q4_K_S.gguf	Q4_K_S	1.619 GB	small, greater quality loss
phi-2-orange-v2-Q4_K_M.gguf	Q4_K_M	1.738 GB	medium, balanced quality - recommended
phi-2-orange-v2-Q5_0.gguf	Q5_0	1.933 GB	legacy; medium, balanced quality - prefer using Q4_K_M
phi-2-orange-v2-Q5_K_S.gguf	Q5_K_S	1.933 GB	large, low quality loss - recommended
phi-2-orange-v2-Q5_K_M.gguf	Q5_K_M	2.003 GB	large, very low quality loss - recommended
phi-2-orange-v2-Q6_K.gguf	Q6_K	2.285 GB	very large, extremely low quality loss
phi-2-orange-v2-Q8_0.gguf	Q8_0	2.958 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/phi-2-orange-v2-GGUF --include "phi-2-orange-v2-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/phi-2-orange-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'