hamelsmu / ft-driftLinks
Check for data drift between two OpenAI multi-turn chat jsonl files.
☆39Updated last year
Alternatives and similar repositories for ft-drift
Users that are interested in ft-drift are comparing it to the libraries listed below
Sorting:
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆33Updated last year
- experiments with inference on llama☆103Updated last year
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆32Updated 2 months ago
- ☆80Updated last year
- Supervised instruction finetuning for LLM with HF trainer and Deepspeed☆36Updated 2 years ago
- ☆53Updated 10 months ago
- Chunk your text using gpt4o-mini more accurately☆44Updated last year
- ☆78Updated last year
- ☆15Updated 2 years ago
- Multi-threaded matrix multiplication and cosine similarity calculations for dense and sparse matrices. Appropriate for calculating the K …☆85Updated 11 months ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆107Updated 2 months ago
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆153Updated 5 months ago
- Generalist and Lightweight Model for Text Classification☆166Updated last week
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆103Updated last year
- Code for NeurIPS LLM Efficiency Challenge☆59Updated last year
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last month
- ☆44Updated 2 years ago
- Command Line Interface for Hugging Face Inference Endpoints☆66Updated last year
- ☆160Updated last year
- Framework for building and maintaining self-updating prompts for LLMs☆64Updated last year
- Nearly Inference Free Embeddings: make your RAG queries 500x faster☆66Updated last month
- Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and te…☆44Updated last year
- Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da☆118Updated 8 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆67Updated 2 months ago
- ☆198Updated last year
- ☆48Updated last year
- 🤝 Trade any tensors over the network☆30Updated 2 years ago
- ☆23Updated 2 years ago
- PyTorch implementation for MRL☆20Updated last year
- ☆84Updated last year