model: add Clover support (#31306)
* model : add AR-only Clover MoE support Add GGUF conversion, model loading, and causal hybrid attention for Clover, reusing shared attention, recurrent-state, MoE, and LoRA helpers. * Update tests/test-llama-archs.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> * convert : filter Clover tensors using filter_tensors * clover : use the standard ssm_a tensor name --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
This commit is contained in:
1 parent
1b6935b227
commit
e4b6c8ca6a
11 files changed
+560
-6
No files matched your search
@@ -38,6 +38,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
|
||||
{ LLM_ARCH_QWEN3, "qwen3" },
|
||||
{ LLM_ARCH_FLINT, "flint" },
|
||||
{ LLM_ARCH_QWEN3MOE, "qwen3moe" },
|
||||
{ LLM_ARCH_CLOVER_MOE, "clover_moe" },
|
||||
{ LLM_ARCH_QWEN3NEXT, "qwen3next" },
|
||||
{ LLM_ARCH_QWEN3VL, "qwen3vl" },
|
||||
{ LLM_ARCH_QWEN3VLMOE, "qwen3vlmoe" },
|
||||
@@ -1292,6 +1293,7 @@ bool llm_arch_is_hybrid(const llm_arch & arch) {
|
||||
case LLM_ARCH_GLM5_NEXT:
|
||||
case LLM_ARCH_QWEN35:
|
||||
case LLM_ARCH_QWEN35MOE:
|
||||
case LLM_ARCH_CLOVER_MOE:
|
||||
case LLM_ARCH_QWEN4EXP:
|
||||
case LLM_ARCH_DEEPSEEK4:
|
||||
case LLM_ARCH_DEEPSEEK41:
|
||||
@@ -1319,6 +1321,7 @@ bool llm_arch_supports_rs_rollback(const llm_arch & arch) {
|
||||
case LLM_ARCH_KIMI_K3:
|
||||
case LLM_ARCH_QWEN35:
|
||||
case LLM_ARCH_QWEN35MOE:
|
||||
case LLM_ARCH_CLOVER_MOE:
|
||||
case LLM_ARCH_QWEN4EXP:
|
||||
case LLM_ARCH_DEEPSEEK4:
|
||||
case LLM_ARCH_DEEPSEEK41:
|
||||
@@ -1354,6 +1357,7 @@ bool llm_arch_supports_mixed_batch(const llm_arch & arch) {
|
||||
|
||||
bool llm_arch_supports_sm_tensor(const llm_arch & arch) {
|
||||
switch (arch) {
|
||||
case LLM_ARCH_CLOVER_MOE:
|
||||
case LLM_ARCH_GROK:
|
||||
case LLM_ARCH_MPT:
|
||||
case LLM_ARCH_PLAMO2:
|
||||
|
||||
Reference in new issue
Block a user