model : support vision LiquidAI LFM2-VL family (#15347)
* wip lfm2 vision model * Fix conv weight * Implement dynamic resolution * Fix cuda * support LFM2-VL-450M * happy CI * Remove extra `ggml_conv` and put others into the right place Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
@@ -82,6 +82,7 @@
|
||||
#define TN_MVLM_PROJ_PEG "mm.model.peg.%d.%s"
|
||||
#define TN_IMAGE_NEWLINE "model.image_newline"
|
||||
#define TN_MM_INP_NORM "mm.input_norm.weight"
|
||||
#define TN_MM_INP_NORM_B "mm.input_norm.bias"
|
||||
#define TN_MM_INP_PROJ "mm.input_projection.weight" // gemma3
|
||||
#define TN_MM_SOFT_EMB_N "mm.soft_emb_norm.weight" // gemma3
|
||||
#define TN_MM_PROJECTOR "mm.model.fc.weight" // idefics3
|
||||
@@ -133,6 +134,7 @@ enum projector_type {
|
||||
PROJECTOR_TYPE_QWEN2A,
|
||||
PROJECTOR_TYPE_QWEN25O, // will be replaced by QWEN2A or QWEN25VL depending on clip_ctx
|
||||
PROJECTOR_TYPE_VOXTRAL,
|
||||
PROJECTOR_TYPE_LFM2,
|
||||
PROJECTOR_TYPE_UNKNOWN,
|
||||
};
|
||||
|
||||
@@ -153,6 +155,7 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
|
||||
{ PROJECTOR_TYPE_QWEN2A, "qwen2a"},
|
||||
{ PROJECTOR_TYPE_QWEN25O, "qwen2.5o"},
|
||||
{ PROJECTOR_TYPE_VOXTRAL, "voxtral"},
|
||||
{ PROJECTOR_TYPE_LFM2, "lfm2"},
|
||||
};
|
||||
|
||||
static projector_type clip_projector_type_from_string(const std::string & str) {
|
||||
|
||||
Reference in New Issue
Block a user