model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252)
* model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: Xuan-Son Nguyen <son@huggingface.co> Assisted-by: Claude Opus 5.5 * tests : set the SWA rope base of the LFM3 test model Assisted-by: Claude Opus 5.5 * llama : enable recurrent state rollback for LFM3 Assisted-by: Claude Opus 5.5 * Apply batched suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: Tarek Dakhran <github@dakhran.com> * gguf-py : align the lfm3vl mapping comments Assisted-by: Claude Opus 5.5 * llama : fix CRLF line endings from the review suggestions Assisted-by: Claude Opus 5.5 * tests : add the LFM3 Metal fusion baseline Assisted-by: Claude Opus 5.5 * llama : keep the LFM3-VL depthwise conv kernels in F32 when quantizing Assisted-by: Claude Opus 5.5 --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
This commit is contained in:
23 files changed
+1070
-5
No files matched your search
@@ -342,6 +342,9 @@ static bool tensor_allows_quantization(const llama_model_quantize_params * param
|
||||
quantize &= name.find("ssm_conv1d") == std::string::npos;
|
||||
quantize &= name.find("shortconv.conv.weight") == std::string::npos;
|
||||
|
||||
// do not quantize LFM3-VL's depthwise conv kernels, CONV_2D_DW takes F32 kernels
|
||||
quantize &= name.find("conv2d_spatial.weight") == std::string::npos;
|
||||
|
||||
// do not quantize MiniMax's indexer projection weights, they are tiny
|
||||
quantize &= name.find("indexer.k_proj.weight") == std::string::npos;
|
||||
quantize &= name.find("indexer.q_proj.weight") == std::string::npos;
|
||||
|
||||
Reference in new issue
Block a user