model: Add support for CogVLM model (#15002)

* Added GGUF mappings for CogVLM model

* Add tensor mapping for CogVLM visual encoder

* Add CogVLM to conversion script, no vision part yet

* Added CogVLM vision model to conversion script

* Add graph for CogVLM CLIP model

* Add graph for CogVLM

* Fixes for CogVLM. Now compiles.

* Model now runs

* Fixes for cogvlm graph

* Account for graph context change after rebase

* Changes for whitespace

* Changes in convert script according to comments

* Switch CogVLM LLM graph to merged QKV tensor

* Use rope_type variable instead of direct definition

* Change CogVLM CLIP encoder to use SWIGLU

* Switch CogVLM CLIP to use merged QKV

* Apply rebase edits and remove ggml_cont call that is now unnecessary

* clean up

---------

Co-authored-by: Xuan Son Nguyen <[email protected]>

Author: Tianyue-Zhao

convert_hf_to_gguf.py

@@ -1528,7 +1528,7 @@ def set_gguf_parameters(self):
             self.gguf_writer.add_vision_embedding_length(self.find_vparam(["hidden_size"]))
             self.gguf_writer.add_vision_feed_forward_length(self.find_vparam(["intermediate_size"]))
             self.gguf_writer.add_vision_block_count(self.find_vparam(self.n_block_keys))
-            self.gguf_writer.add_vision_head_count(self.find_vparam(["num_attention_heads"]))
+            self.gguf_writer.add_vision_head_count(self.find_vparam(["num_attention_heads", "num_heads"]))
 
             # preprocessor config
             image_mean = _MISTRAL_COMMON_DATASET_MEAN if self.is_mistral_format else self.preprocessor_config["image_mean"]
@@ -9493,6 +9493,37 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
 
         return [] # skip other tensors
 
+
+@ModelBase.register("CogVLMForCausalLM")
+class CogVLMVisionModel(MmprojModel):
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+        self.gguf_writer.add_vision_attention_layernorm_eps(self.hparams.get("layer_norm_eps", 1e-6))
+        self.gguf_writer.add_clip_projector_type(gguf.VisionProjectorType.COGVLM)
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        del bid  # unused
+
+        if not name.startswith("model.vision."):
+            return []
+
+        return [(self.map_tensor_name(name), data_torch)]
+
+
+@ModelBase.register("CogVLMForCausalLM")
+class CogVLMModel(LlamaModel):
+    model_arch = gguf.MODEL_ARCH.COGVLM
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        del bid  # unused
+
+        # block vision tensors
+        if name.startswith("model.vision."):
+            return []
+
+        return [(self.map_tensor_name(name), data_torch)]
+
 ###### CONVERSION LOGIC ######
 
 

gguf-py/gguf/constants.py

@@ -420,6 +420,7 @@ class MODEL_ARCH(IntEnum):
     SEED_OSS         = auto()
     GROVEMOE         = auto()
     APERTUS          = auto()
+    COGVLM           = auto()
 
 
 class VISION_PROJECTOR_TYPE(IntEnum):
@@ -430,6 +431,7 @@ class VISION_PROJECTOR_TYPE(IntEnum):
     GLM_EDGE  = auto()
     MERGER    = auto()
     GEMMA3    = auto()
+    COGVLM    = auto()
 
 
 class MODEL_TENSOR(IntEnum):
@@ -600,6 +602,11 @@ class MODEL_TENSOR(IntEnum):
     SHORTCONV_CONV       = auto()
     SHORTCONV_INPROJ     = auto()
     SHORTCONV_OUTPROJ    = auto()
+    VISEXP_ATTN_QKV      = auto()
+    VISEXP_ATTN_OUT      = auto()
+    VISEXP_GATE          = auto()
+    VISEXP_DOWN          = auto()
+    VISEXP_UP            = auto()
     # vision
     V_MMPROJ             = auto()
     V_MMPROJ_FC          = auto()
@@ -609,6 +616,7 @@ class MODEL_TENSOR(IntEnum):
     V_ENC_EMBD_PATCH     = auto()
     V_ENC_EMBD_POS       = auto()
     V_ENC_INPUT_NORM     = auto()
+    V_ENC_ATTN_QKV       = auto()
     V_ENC_ATTN_Q         = auto()
     V_ENC_ATTN_Q_NORM    = auto()
     V_ENC_ATTN_K         = auto()
@@ -640,6 +648,12 @@ class MODEL_TENSOR(IntEnum):
     V_RESMPL_QUERY       = auto() # minicpmv
     V_TOK_EMBD_IMG_BREAK = auto() # pixtral
     V_MM_PATCH_MERGER    = auto() # mistral small 3.1
+    V_MM_POST_FC_NORM    = auto() # cogvlm
+    V_MM_UP              = auto() # cogvlm
+    V_MM_DOWN            = auto() # cogvlm
+    V_MM_GATE            = auto() # cogvlm
+    V_TOK_BOI            = auto() # cogvlm
+    V_TOK_EOI            = auto() # cogvlm
     # audio (mtmd)
     A_ENC_EMBD_POS       = auto()
     A_ENC_CONV1D         = auto()
@@ -766,6 +780,7 @@ class MODEL_TENSOR(IntEnum):
     MODEL_ARCH.SEED_OSS:         "seed_oss",
     MODEL_ARCH.GROVEMOE:         "grovemoe",
     MODEL_ARCH.APERTUS:          "apertus",
+    MODEL_ARCH.COGVLM:           "cogvlm",
 }
 
 VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
@@ -946,6 +961,11 @@ class MODEL_TENSOR(IntEnum):
     MODEL_TENSOR.SHORTCONV_CONV:            "blk.{bid}.shortconv.conv",
     MODEL_TENSOR.SHORTCONV_INPROJ:          "blk.{bid}.shortconv.in_proj",
     MODEL_TENSOR.SHORTCONV_OUTPROJ:         "blk.{bid}.shortconv.out_proj",
+    MODEL_TENSOR.VISEXP_ATTN_QKV:           "blk.{bid}.vis_attn_qkv",
+    MODEL_TENSOR.VISEXP_ATTN_OUT:           "blk.{bid}.vis_attn_output",
+    MODEL_TENSOR.VISEXP_GATE:               "blk.{bid}.vis_gate",
+    MODEL_TENSOR.VISEXP_DOWN:               "blk.{bid}.vis_down",
+    MODEL_TENSOR.VISEXP_UP:                 "blk.{bid}.vis_up",
     # vision
     MODEL_TENSOR.V_MMPROJ:                  "mm.{bid}",
     MODEL_TENSOR.V_MMPROJ_FC:               "mm.model.fc",
@@ -954,6 +974,7 @@ class MODEL_TENSOR(IntEnum):
     MODEL_TENSOR.V_ENC_EMBD_CLS:            "v.class_embd",
     MODEL_TENSOR.V_ENC_EMBD_PATCH:          "v.patch_embd",
     MODEL_TENSOR.V_ENC_EMBD_POS:            "v.position_embd",
+    MODEL_TENSOR.V_ENC_ATTN_QKV:            "v.blk.{bid}.attn_qkv",
     MODEL_TENSOR.V_ENC_ATTN_Q:              "v.blk.{bid}.attn_q",
     MODEL_TENSOR.V_ENC_ATTN_Q_NORM:         "v.blk.{bid}.attn_q_norm",
     MODEL_TENSOR.V_ENC_ATTN_K:              "v.blk.{bid}.attn_k",
@@ -986,6 +1007,12 @@ class MODEL_TENSOR(IntEnum):
     MODEL_TENSOR.V_RESMPL_QUERY:            "resampler.query",
     MODEL_TENSOR.V_TOK_EMBD_IMG_BREAK:      "v.token_embd.img_break", # pixtral
     MODEL_TENSOR.V_MM_PATCH_MERGER:         "mm.patch_merger", # mistral small 3.1
+    MODEL_TENSOR.V_MM_POST_FC_NORM:         "mm.post_fc_norm", # cogvlm
+    MODEL_TENSOR.V_MM_UP:                   "mm.up",
+    MODEL_TENSOR.V_MM_DOWN:                 "mm.down",
+    MODEL_TENSOR.V_MM_GATE:                 "mm.gate",
+    MODEL_TENSOR.V_TOK_BOI:                 "v.boi",
+    MODEL_TENSOR.V_TOK_EOI:                 "v.eoi",
     # audio (mtmd)
     MODEL_TENSOR.A_ENC_EMBD_POS:            "a.position_embd",
     MODEL_TENSOR.A_ENC_CONV1D:              "a.conv1d.{bid}",
@@ -1023,6 +1050,7 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.V_ENC_EMBD_PATCH,
         MODEL_TENSOR.V_ENC_EMBD_POS,
         MODEL_TENSOR.V_ENC_INPUT_NORM,
+        MODEL_TENSOR.V_ENC_ATTN_QKV,
         MODEL_TENSOR.V_ENC_ATTN_Q,
         MODEL_TENSOR.V_ENC_ATTN_Q_NORM,
         MODEL_TENSOR.V_ENC_ATTN_K,
@@ -1054,6 +1082,12 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.V_RESMPL_QUERY,
         MODEL_TENSOR.V_TOK_EMBD_IMG_BREAK,
         MODEL_TENSOR.V_MM_PATCH_MERGER,
+        MODEL_TENSOR.V_MM_POST_FC_NORM,
+        MODEL_TENSOR.V_MM_UP,
+        MODEL_TENSOR.V_MM_DOWN,
+        MODEL_TENSOR.V_MM_GATE,
+        MODEL_TENSOR.V_TOK_BOI,
+        MODEL_TENSOR.V_TOK_EOI,
         # audio
         MODEL_TENSOR.A_ENC_EMBD_POS,
         MODEL_TENSOR.A_ENC_CONV1D,
@@ -2837,6 +2871,23 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.FFN_DOWN_CHEXP,
         MODEL_TENSOR.FFN_UP_CHEXP,
     ],
+    MODEL_ARCH.COGVLM: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_QKV,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+        MODEL_TENSOR.VISEXP_ATTN_QKV,
+        MODEL_TENSOR.VISEXP_ATTN_OUT,
+        MODEL_TENSOR.VISEXP_GATE,
+        MODEL_TENSOR.VISEXP_UP,
+        MODEL_TENSOR.VISEXP_DOWN,
+    ],
     # TODO
 }
 
@@ -3063,6 +3114,7 @@ class VisionProjectorType:
     LFM2 = "lfm2"
     KIMIVL = "kimivl"
     LIGHTONOCR = "lightonocr"
+    COGVLM = "cogvlm"
 
 
 # Items here are (block size, type size)