huggingface / ethics-scripts
☆14Updated last year
Related projects ⓘ
Alternatives and complementary repositories for ethics-scripts
- Scripts supporting the development and serving the Roots Search Tool - https://hf.co/spaces/bigscience-data/roots-search☆10Updated last year
- Hugging Face and Pyserini interoperability☆19Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆18Updated last year
- 🤗 Disaggregators: Curated data labelers for in-depth analysis.☆65Updated last year
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found he…☆31Updated last year
- Evaluate Transformers from the Hub 🔥☆13Updated 11 months ago
- Tool to take your ML model from local to production with one-line of code.☆23Updated 10 months ago
- ☆14Updated last year
- Efficiently computing & storing token n-grams from large corpora☆15Updated last month
- Supervised instruction finetuning for LLM with HF trainer and Deepspeed☆34Updated last year
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated last week
- Low-Rank Adaptation of Large Language Models clean implementation☆9Updated last year
- ☆14Updated 3 months ago
- ☆15Updated 2 weeks ago
- ☆13Updated last year
- **ARCHIVED** Filesystem interface to 🤗 Hub☆56Updated last year
- Scripts to parse arxiv documents for NLP tasks☆17Updated last year
- Developing tools to automatically analyze datasets☆70Updated 3 weeks ago
- Simple implementation of a GPT (training and inference) in PyTorch.☆10Updated 11 months ago
- Everything for the Paper: 'Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing'☆15Updated 11 months ago
- Exploration using DSPy to optimize modules to maximize performance on the OpenToM dataset☆13Updated 8 months ago
- ☆24Updated 2 years ago
- Unleash the full potential of exascale LLMs on consumer-class GPUs, proven by extensive benchmarks, with no long-term adjustments and min…☆23Updated last week
- Train a production grade GPT in less than 400 lines of code. Better than Karpathy's verison and GIGAGPT☆15Updated last week
- code for paper "Accessing higher dimensions for unsupervised word translation"☆21Updated last year
- Hosting examples of interactive datamapplot output☆19Updated last month
- ☆17Updated 6 months ago
- ☆20Updated 9 months ago
- Hugging Face's Zapier Integration 🤗⚡️☆47Updated last year