4.0.9

• github action for jazzy
• SmolLM2 model added
• requirements removed (lark, packaging)
• llama.cpp b4011

4.0.8

• fixing llama_rag demo
• Tail-Free sampling removed
• signal removed from mains
• llama.cpp b3995

4.0.7

• DRY sampling
• llama.cpp b3982

4.0.6

• Dockerfile created
• CI github actions for formatter and docker build
• python formatted with black
• llama.cpp b3974

4.0.5

• lark added to requirements
• normalization types for embeddings
• llama.cpp b3962

4.0.4

• vendor CMakeLists fixed
• llama.cpp b3933

4.0.3

• new XTC sampling added
• new system_prompt param
• llama.cpp b3923

This version does not compile due to errors in the vendor CMakeLists

4.0.2

• common prefix added for llama.cpp commons
• llama.cpp b3906

This version does not compile due to errors in the vendor CMakeLists

4.0.1

• llama_rag_demo fixed
• llama.cpp b3889

4.0.0

• reranking added
• separate LLM, embedding models and reranking models
• new services (reranking and detokenize)
• models for reranking and embeddings added
• vicuna promopt added
• llama namespace removed from LlamaClientNode
• full demo with LLM + chat template + RAG + reranking + stream
• README:
  • model shards example added
  • reranking langchain and demo added
  • embedding demo added
  • minor fixes
• langchain reranking added
• langchain upgraded to 0.3
• llama.cpp b3870