v3.0.0-beta.45

3.0.0-beta.45 (2024-09-19)

Bug Fixes

• improve performance of parallel evaluation from multiple contexts (#309) (4b3ad61)
• Llama 3.1 chat wrapper standard chat history (#309) (4b3ad61)
• adapt to llama.cpp sampling refactor (#309) (4b3ad61)
• Llama 3 Instruct function calling (#309) (4b3ad61)
• don't preload prompt in the chat command when using --printTimings or --meter (#309) (4b3ad61)
• more stable Jinja template matching (#309) (4b3ad61)

Features

• inspect estimate command (#309) (4b3ad61)
• move seed option to the prompt level (#309) (4b3ad61)
• Functionary v3 support (#309) (4b3ad61)
• Mistral chat wrapper (#309) (4b3ad61)
• improve Llama 3.1 chat template detection (#309) (4b3ad61)
• change autoDisposeSequence default to false (#309) (4b3ad61)
• move download, build and clear commands to be subcommands of a source command (#309) (4b3ad61)
• simplify TokenBias (#309) (4b3ad61)
• better threads default value (#309) (4b3ad61)
• make LlamaEmbedding an object (#309) (4b3ad61)
• HF_TOKEN env var support for reading GGUF file metadata (#309) (4b3ad61)
• TemplateChatWrapper: custom history template for each message role (#309) (4b3ad61)
• more helpful inspect gpu command (#309) (4b3ad61)
• all tokenizer tokens iterator (#309) (4b3ad61)
• failed context creation automatic remedy (#309) (4b3ad61)
• abort generation support in CLI commands (#309) (4b3ad61)
• --gpuLayers max and --contextSize max flag support for inspect estimate command (#309) (4b3ad61)
• extract all prebuilt binaries to external modules (#309) (4b3ad61)
• updated docs (#309) (4b3ad61)
• combine model downloaders (#309) (4b3ad61)
• feat(electron example template): update badge, scroll anchoring, table support (#309) (4b3ad61)

---

Shipped with llama.cpp release b3785

To use the latest llama.cpp release available, run npx -n node-llama-cpp source download --release latest. (learn more)

v2.8.16

2.8.16 (2024-09-03)

Bug Fixes

• bump llama.cpp release used in prebuilt binaries (#305) (660651a)
• update documentation website URL (#306) (51265c8)

v3.0.0-beta.44

3.0.0-beta.44 (2024-08-10)

Bug Fixes

• revert to the latest stable Metal llama.cpp release (#297) (bf12e9c)

---

Shipped with llama.cpp release b3543

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.43

3.0.0-beta.43 (2024-08-09)

Bug Fixes

• more cases of unknown characters in generation streaming (#295) (ecaef63)

---

Shipped with llama.cpp release b3560

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.42

3.0.0-beta.42 (2024-08-07)

Bug Fixes

• unkown characters in generation streaming (#293) (097b3ec)

---

Shipped with llama.cpp release b3541

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v2.8.15

2.8.15 (2024-08-06)

Bug Fixes

• adapt to llama.cpp breaking changes (#291) (c4b5d80)

v3.0.0-beta.41

3.0.0-beta.41 (2024-08-02)

Bug Fixes

• CUDA context creation (#285) (a2b2bc3)
• detokenizer unpredictable text length (#285) (a2b2bc3)

---

Shipped with llama.cpp release b3504

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.40

3.0.0-beta.40 (2024-07-30)

Bug Fixes

• update model recommendations (#276) (826334b)

Features

• model downloader: use HF_TOKEN when needed (#276) (826334b)

---

Shipped with llama.cpp release b3488

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.39

3.0.0-beta.39 (2024-07-28)

Bug Fixes

• Gemma chat wrapper bug (#273) (e3e0994)
• GGUF metadata nested key conflicts (#273) (e3e0994)
• adapt to llama.cpp breaking changes (#273) (e3e0994)
• preserve function calling chunks (#273) (e3e0994)
• format JSON objects like models expect (#273) (e3e0994)

Features

• Llama 3.1 support (#273) (e3e0994)
• Phi-3 support (#273) (e3e0994)
• model metadata overrides (#273) (e3e0994)
• use LoRA on a context instead of on a model (#273) (e3e0994)
• onTextChunk option (#273) (e3e0994)

---

Shipped with llama.cpp release b3479

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v2.8.14

2.8.14 (2024-07-26)

Bug Fixes

• prebuilt binaries (#272) (e539e5b)