README.md

metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:3000
  - loss:MultipleNegativesRankingLoss
  - llama-cpp
  - gguf-my-repo
base_model: trbeers/distilroberta-base-nli-v2
datasets:
  - sentence-transformers/all-nli
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: >-
      An Indian woman is washing and cleaning dirty laundry at a lake and in the
      background is a kid who appears to have jumped into the lake.
    sentences:
      - An Indian woman is doing her laundry in a lake.
      - An Indian woman is putting her laundry into the machine.
      - A girl is playing with a Slinky.
  - source_sentence: Nine women in white robes with hoods walk on plush, green grass.
    sentences:
      - The women each have one head.
      - Two friends sitting on step at their job.
      - The woman is alone and asleep in her bedroom.
  - source_sentence: >-
      Under a blue sky with white clouds, a child reaches up to touch the
      propeller of a plane standing parked on a field of grass.
    sentences:
      - A child is reaching to touch the propeller of a plane.
      - The boy is sitting
      - A child is playing with a ball.
  - source_sentence: A man and a woman are talking in a park
    sentences:
      - A man is heading to his house of worship.
      - A pair of people are talking outdoors.
      - A man and woman are talking in the aquarium.
  - source_sentence: A man running a marathon talks to his friend.
    sentences:
      - People watching hot air balloons inflating.
      - There is a man running.
      - There are people canoeing down a river.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on distilbert/distilroberta-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.7444932434233196
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7769282355085634
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7502489213535852
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7574428535049513
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.752089041601621
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7583983155030144
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.49365896310259416
            name: Pearson Dot
          - type: spearman_dot
            value: 0.49513705166832495
            name: Spearman Dot
          - type: pearson_max
            value: 0.752089041601621
            name: Pearson Max
          - type: spearman_max
            value: 0.7769282355085634
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.7101248020205797
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7072744861979087
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7133109440593921
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.6966728374126535
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7142547715068376
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.6959833440145297
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.4503698330540162
            name: Pearson Dot
          - type: spearman_dot
            value: 0.43425556993054526
            name: Spearman Dot
          - type: pearson_max
            value: 0.7142547715068376
            name: Pearson Max
          - type: spearman_max
            value: 0.7072744861979087
            name: Spearman Max

Sleem247/distilroberta-base-nli-v2-Q8_0-GGUF

This model was converted to GGUF format from trbeers/distilroberta-base-nli-v2 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 (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Sleem247/distilroberta-base-nli-v2-Q8_0-GGUF --hf-file distilroberta-base-nli-v2-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Sleem247/distilroberta-base-nli-v2-Q8_0-GGUF --hf-file distilroberta-base-nli-v2-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.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Sleem247/distilroberta-base-nli-v2-Q8_0-GGUF --hf-file distilroberta-base-nli-v2-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Sleem247/distilroberta-base-nli-v2-Q8_0-GGUF --hf-file distilroberta-base-nli-v2-q8_0.gguf -c 2048