Pascal
ba3c05f71d
Copilot Setup Steps / copilot-setup-steps (push) Has been cancelled
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Has been cancelled
Python check requirements.txt / check-requirements (push) Has been cancelled
Python Type-Check / python type-check (push) Has been cancelled
Update Operations Documentation / update-ops-docs (push) Has been cancelled
* model: add Muse Spark Open (text, vision and audio) Muse Spark Open is a latent space MoE: the residual stream stays at 8192 while the 256 experts live in 4096, with a projection down and up around them, top-8 sigmoid routing with a correction bias. Attention interleaves three sliding layers at a 2048 window with rope for one global layer without rope, with a sigmoid output gate and a weightless QK-norm. Residuals are norm preserving, their gate is folded at conversion time. Vision reuses the Muse Glimmer tower. Audio is a causal convolutional pyramid with no attention and no spectrogram, four stages folding 16, 6, 5 and 4 samples into the channel dim, one embedding per 80 ms of 24 kHz. The quantizer keeps the latent projections and the attention gate at Q8_0, a little over 1% of the weights, since the whole residual stream passes through them and the low-bit types turned the output into a repeating loop. The model saver writes the post norm epsilon, and the arch is registered in test-llama-archs. Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> * Muse Spark: drop the redundant forward expand * Muse Spark: drop the redundant forward expand and tighten the comments * Update src/llama-quant.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update src/llama-graph.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * Update conversion/muse_spark.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Pedro Cuenca <pedro@huggingface.co> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
26 lines
1.1 KiB
CMake
26 lines
1.1 KiB
CMake
# Specialized chat template parsers, listed explicitly so that adding or removing one re-runs CMake instead of leaving an incremental build stale.
|
|
|
|
set(LLAMA_CHAT_PARSERS_SOURCES
|
|
${CMAKE_CURRENT_LIST_DIR}/parsers.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/parsers.h
|
|
${CMAKE_CURRENT_LIST_DIR}/cohere2moe.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/deepseek.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/functionary-v3-2.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/gemma4.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/gigachat-v3.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/gpt-oss.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/k2-horizon.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/kimi-k2.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/kimi-k3.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/ling3.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/lfm2.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/llm-jp-harmony.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/minicpm5.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/minimax-m3.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/ministral3.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/muse-glimmer.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/muse-spark.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/qwen3-coder.cpp
|
|
${CMAKE_CURRENT_LIST_DIR}/translate-gemma.cpp
|
|
)
|