README.md

metadata

language:
  - en
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:101762
  - loss:TripletLoss
  - llama-cpp
  - gguf-my-repo
base_model: ravi259/distilroberta-base-sentence-transformer_finetuned
widget:
  - source_sentence: A dog is in the water.
    sentences:
      - The woman is wearing green.
      - The dog is rolling around in the grass.
      - >-
        A brown dog swims through water outdoors with a tennis ball in its
        mouth.
  - source_sentence: A dog is swimming.
    sentences:
      - a black dog swimming in the water with a tennis ball in his mouth
      - A dog with yellow fur swims, neck deep, in water.
      - A brown dog running through a large orange tube.
  - source_sentence: A dog is swimming.
    sentences:
      - A dog with golden hair swims through water.
      - A golden haired dog is lying in a boat that is traveling on a lake.
      - A dog with golden hair swims through water.
  - source_sentence: A dog is swimming.
    sentences:
      - A tan dog splashes as he swims through the water.
      - A man and young boy asleep in a chair.
      - A dog in a harness chasing a red ball.
  - source_sentence: A dog is in the water.
    sentences:
      - A big brown dog jumps into a swimming pool on the backyard.
      - Wet brown dog swims towards camera.
      - The dog is rolling around in the grass.
datasets:
  - embedding-data/QQP_triplets
  - sentence-transformers/all-nli
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on distilbert/distilroberta-base
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: all nli dev
          type: all-nli-dev
        metrics:
          - type: cosine_accuracy
            value: 0.9556500315666199
            name: Cosine Accuracy
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: all nli test
          type: all-nli-test
        metrics:
          - type: cosine_accuracy
            value: 0.9048267602920532
            name: Cosine Accuracy

Sleem247/distilroberta-base-sentence-transformer_finetuned-Q8_0-GGUF

This model was converted to GGUF format from ravi259/distilroberta-base-sentence-transformer_finetuned 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-sentence-transformer_finetuned-Q8_0-GGUF --hf-file distilroberta-base-sentence-transformer_finetuned-q8_0.gguf -p "The meaning to life and the universe is"

Server:

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

or

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