2 Releases published by 1 person

• v0.4.1 Release 0.4.1

  published Nov 17, 2024

• v0.4.2 Release 0.4.2

  published Nov 21, 2024

8 Pull requests merged by 3 people

• feat: sync llama.cpp

  #95 merged Nov 21, 2024

• feat: support multiple lora files & dynamic apply / remove lora

  #92 merged Nov 21, 2024

• Update code example to load the model info before initializing context

  #94 merged Nov 21, 2024

• Expose DRY Sampler [Incomplete]

  #91 merged Nov 18, 2024

• feat(cpp): remove unused json and json-schema-to-grammar in common

  #90 merged Nov 17, 2024

• feat: sync llama.cpp

  #89 merged Nov 17, 2024

• feat: update embedding method

  #88 merged Nov 16, 2024

• feat: add static method for read model info from gguf

  #87 merged Nov 16, 2024

3 Issues closed by 1 person

• Expose Template Parameter for getFormattedChat

  #84 closed Nov 16, 2024

• Unable to import model

  #76 closed Nov 16, 2024

• Embbedding models without LLAMA_POOLING_TYPE_NONE are broken

  #74 closed Nov 16, 2024

1 Issue opened by 1 person

• Running initLlama with lora / lora_scaled set, fails to load context and crashes app.

  #86 opened Nov 15, 2024

1 Unresolved conversation

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• App crashes/closes as soon as I try to load model

  #85 commented on Nov 20, 2024 • 0 new comments