Sleem247/chatbot_sentence-transformer-Q8_0-GGUF
This model was converted to GGUF format from nikatonika/chatbot_sentence-transformer 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/chatbot_sentence-transformer-Q8_0-GGUF --hf-file chatbot_sentence-transformer-q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo Sleem247/chatbot_sentence-transformer-Q8_0-GGUF --hf-file chatbot_sentence-transformer-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/chatbot_sentence-transformer-Q8_0-GGUF --hf-file chatbot_sentence-transformer-q8_0.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo Sleem247/chatbot_sentence-transformer-Q8_0-GGUF --hf-file chatbot_sentence-transformer-q8_0.gguf -c 2048
- Downloads last month
- 10
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for Sleem247/chatbot_sentence-transformer-Q8_0-GGUF
Base model
distilbert/distilroberta-base Finetuned
nikatonika/chatbot_sentence-transformerEvaluation results
- Cosine Accuracy on dev evaluatorself-reported0.981
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Sleem247/chatbot_sentence-transformer-Q8_0-GGUF") sentences = [ "Its personal! [SEP] I put you on uppers and you still yawned. Means its a symptom, of being a big fat liar. Yawning is a side effect of some antidepressants, apparently the ones youre on. Im not on antidepressants Im on SPEEEEEED! Well that means its a symptom of a cerebral tumour. You got six weeks to live. Mr. Welladjusted is as messed up as the rest of us. Whwhy would you keep that a secret? Are you ashamed of recognising how pathetic your life is? Its not a secret. House itsits... its personal! How long has it been personal? Yawnings recent so! either you just started or you changed prescription.", "Yawnings recent so! either you just started or you changed prescription.", "The High Sparrow has hundreds of Faith Militant surrounding him. Ser Gregor will can’t face them all. And he won’t have to. He’ll only have to face one.", "Whoa, whoa, whoa! Hey! Whoa!" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]