README.md

metadata

language:
  - en
  - zh
  - id
  - th
  - vi
  - ms
  - lo
license: apache-2.0
tags:
  - multilingual
  - sea
  - sailor
  - llama-cpp
  - gguf-my-repo
base_model: Qwen/Qwen1.5-7B
datasets:
  - cerebras/SlimPajama-627B
  - Skywork/SkyPile-150B
  - allenai/MADLAD-400
  - cc100
model-index:
  - name: Sailor-7B
    results:
      - task:
          type: text-generation
        dataset:
          name: XQuAD-Thai
          type: XQuAD-Thai
        metrics:
          - type: EM (3-Shot)
            value: 57.88
            name: EM (3-Shot)
          - type: F1 (3-Shot)
            value: 71.06
            name: F1 (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: TyDiQA-Indonesian
          type: TyDiQA-Indonesian
        metrics:
          - type: EM (3-Shot)
            value: 60.53
            name: EM (3-Shot)
          - type: F1 (3-Shot)
            value: 75.42
            name: F1 (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: XQuAD-Vietnamese
          type: XQuAD-Vietnamese
        metrics:
          - type: EM (3-Shot)
            value: 53.81
            name: EM (3-Shot)
          - type: F1 (3-Shot)
            value: 74.62
            name: F1 (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: XCOPA-Thai
          type: XCOPA-Thai
        metrics:
          - type: EM (3-Shot)
            value: 59
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: XCOPA-Indonesian
          type: XCOPA-Indonesian
        metrics:
          - type: EM (3-Shot)
            value: 72.2
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: XCOPA-Vietnamese
          type: XCOPA-Vietnamese
        metrics:
          - type: EM (3-Shot)
            value: 72.2
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: M3Exam-Thai
          type: M3Exam-Thai
        metrics:
          - type: EM (3-Shot)
            value: 30
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: M3Exam-Indonesian
          type: M3Exam-Indonesian
        metrics:
          - type: EM (3-Shot)
            value: 32.88
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: M3Exam-Vietnamese
          type: M3Exam-Vietnamese
        metrics:
          - type: EM (3-Shot)
            value: 44.1
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: BELEBELE-Thai
          type: BELEBELE-Thai
        metrics:
          - type: EM (3-Shot)
            value: 41.56
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: BELEBELE-Indonesian
          type: BELEBELE-Indonesian
        metrics:
          - type: EM (3-Shot)
            value: 44.33
            name: EM (3-Shot)
      - task:
          type: text-generation
        dataset:
          name: BELEBELE-Vietnamese
          type: BELEBELE-Vietnamese
        metrics:
          - type: EM (3-Shot)
            value: 45.33
            name: EM (3-Shot)

NikolayKozloff/Sailor-7B-Q8_0-GGUF

This model was converted to GGUF format from sail/Sailor-7B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo NikolayKozloff/Sailor-7B-Q8_0-GGUF --model sailor-7b.Q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo NikolayKozloff/Sailor-7B-Q8_0-GGUF --model sailor-7b.Q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m sailor-7b.Q8_0.gguf -n 128