How to use ronit01/rag_tuned_minilm_mnr with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("ronit01/rag_tuned_minilm_mnr") sentences = [ "What is the recommended approach if you run out of storage space while experimenting with many LLMs?", ".. py:function:: __init__(self, experiment_name: str, mode: str = \"fit\", experiments_path: str = \"./rapidfire_experiments\") -> None\n\n\t:param experiment_name: Unique name for this experiment\n\t:type experiment_name: str\n\t\n\t:param mode: Mode of this experiment, either :code:`\"fit\"` or :code:`\"eval\"`; default is :code:`\"fit\"`\n\t:type mode: str\n\t\n\t:param experiments_path: Path to a folder to store this experiment's artifacts. Default is ``\"./rapidfire_experiments\"``)\n\t:type experiments_path: str, optional \n\n\t:return: None\n\t:rtype: None", "Recovering Storage Space\n-------\n\nIf you run out of storage space on your machine due to experimenting with lots of LLMs, we \nrecommend clearing out the \".cache\" folder on your home directory that is created by \nHugging Face to import the base models. \nOne experiment's imported models are not needed for another; so, it is safe to delete them.\n\nIf you want to reclaim even more space, look at the artifacts from your experiments and \neither delete some of the files or move them to other/remote storage. \nNote that when you use LoRA adapters, RapidFire AI saves only the trained adapters in the \ncheckpoints of the runs, not the base models.", "Multi-GPU Model Partitioning with FSDP\n-------\n\nRapidFire AI supports automated large model partitioning across GPUs (on the same machine) via PyTorch's native FSDP. \nProvide the relevant FSDP deatils in a config knob, optionally along with the number of GPUs to use for that run. \nThe following notebooks showcase the use of FSDP for SFT with the corresponding LLMs:\n\n* FSDP Lite with base model TinyLlama-1.1B-Chat-v1.0. Needs at least 2x A10 GPUs or equivalent (48 GB total HBM) to work. `View on GitHub <https://github.com/RapidFireAI/rapidfireai/blob/main/tutorial_notebooks/fine-tuning/rf-tutorial-sft-chatqa-fsdp-lite.ipynb>`__\n\n* FSDP Regular with base model Qwen3-32B. Needs at least 4x A10 GPUs or equivalent (96 GB total HBM) to work. `View on GitHub <https://github.com/RapidFireAI/rapidfireai/blob/main/tutorial_notebooks/fine-tuning/rf-tutorial-sft-chatqa.ipynb>`__\n\n* FSDP Large with base model Llama-3-70B-Instruct. Needs at least 8x A10 GPUs or equivalent (192 GB total HBM) to work. `View on GitHub <https://github.com/RapidFireAI/rapidfireai/blob/main/tutorial_notebooks/fine-tuning/rf-tutorial-sft-chatqa-fsdp-large.ipynb>`__\n\n.. important::\n Although the above FSDP tutorial notebooks can work on cheap A10 GPUs, we highly recommend using at least A100s or later GPUs with NVLink support for reasonable runtimes.\n" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
