LlamaTune: Fine-Tune Llama V2 models on chat datasets without writing code

• haven

  5 335 8.2 TypeScript

  LLM fine-tuning and eval (by redotvideo)

  

Many users of our open source deployment server without an ML background have asked us how to fine-tune Llama V2 on their chat datasets - so we created llamatune, a lightweight library that lets you do it without writing code! Llamatune supports lora training with 4-and 8-bit quantization, full fine-tuning and model parallelism out-of-the-box for the 7B, 13B, and 70B parameter Llama models.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project