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"]
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 ######
SEED_OSS = auto()
GROVEMOE = auto()
APERTUS = auto()
+ COGVLM = auto()
class VISION_PROJECTOR_TYPE(IntEnum):
GLM_EDGE = auto()
MERGER = auto()
GEMMA3 = auto()
+ COGVLM = auto()
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()
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()
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()
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] = {
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",
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",
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}",
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,
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,
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
}
LFM2 = "lfm2"
KIMIVL = "kimivl"
LIGHTONOCR = "lightonocr"
+ COGVLM = "cogvlm"
# Items here are (block size, type size)
"backbone.final_layer_norm", # wavtokenizer
"model.norm", # llama4
"model.transformer.ln_f", # llada
+ "model.norm", # cogvlm
),
# Rope frequencies
"encoder.layer.{bid}.layer_norm_1", # jina-v2-code
"rwkv.blocks.{bid}.ln2", # rwkv6
"model.layers.{bid}.ln2", # rwkv7
+ "model.layers.{bid}.post_attention_layernorm", # cogvlm
),
# Attention query-key-value
"encoder.layers.{bid}.self_attention.query_key_value", # chatglm
"transformer.layers.{bid}.attn.qkv_proj", # openelm
"transformer_encoder.{bid}.qkv", # neobert
+ "model.layers.{bid}.self_attn.language_expert_query_key_value", # cogvlm
),
# Attention query
"model.transformer.blocks.{bid}.attn_out", # llada
"layers.{bid}.self_attn.o_proj", # qwen3-embedding
"backbone.layers.{bid}.mixer.o_proj", # nemotron-h
+ "model.layers.{bid}.self_attn.language_expert_dense", # cogvlm
),
# Attention output norm
"model.transformer.blocks.{bid}.up_proj", # llada
"layers.{bid}.mlp.up_proj", # qwen3-embedding
"backbone.layers.{bid}.mixer.up_proj", # nemotron-h
+ "model.layers.{bid}.mlp.language_mlp.up_proj", # cogvlm
),
MODEL_TENSOR.FFN_UP_EXP: (
# Feed-forward gate
MODEL_TENSOR.FFN_GATE: (
- "model.layers.{bid}.mlp.gate_proj", # llama-hf refact olmo2
- "layers.{bid}.mlp.gate_proj", # embeddinggemma
- "layers.{bid}.feed_forward.w1", # llama-pth
- "transformer.h.{bid}.mlp.w2", # qwen
- "transformer.h.{bid}.mlp.c_fc2", # jais
- "model.layers.layers.{bid}.mlp.gate_proj", # plamo
- "model.layers.{bid}.feed_forward.w1", # internlm2
- "encoder.layers.{bid}.mlp.fc12", # nomic-bert
- "encoder.layer.{bid}.mlp.gated_layers_w", # jina-bert-v2 (split up/gate, no longer used)
- "transformer.h.{bid}.mlp.linear_1", # refact
- "model.layers.{bid}.residual_mlp.w1", # arctic
- "transformer.h.{bid}.mlp.c_fc_0", # exaone
- "model.layers.{bid}.feed_forward.gate_proj", # llama4 jamba granite-hybrid
- "model.transformer.blocks.{bid}.ff_proj", # llada
- "layers.{bid}.mlp.gate_proj", # qwen3-embedding
+ "model.layers.{bid}.mlp.gate_proj", # llama-hf refact olmo2
+ "layers.{bid}.mlp.gate_proj", # embeddinggemma
+ "layers.{bid}.feed_forward.w1", # llama-pth
+ "transformer.h.{bid}.mlp.w2", # qwen
+ "transformer.h.{bid}.mlp.c_fc2", # jais
+ "model.layers.layers.{bid}.mlp.gate_proj", # plamo
+ "model.layers.{bid}.feed_forward.w1", # internlm2
+ "encoder.layers.{bid}.mlp.fc12", # nomic-bert
+ "encoder.layer.{bid}.mlp.gated_layers_w", # jina-bert-v2 (split up/gate, no longer used)
+ "transformer.h.{bid}.mlp.linear_1", # refact
+ "model.layers.{bid}.residual_mlp.w1", # arctic
+ "transformer.h.{bid}.mlp.c_fc_0", # exaone
+ "model.layers.{bid}.feed_forward.gate_proj", # llama4 jamba granite-hybrid
+ "model.transformer.blocks.{bid}.ff_proj", # llada
+ "layers.{bid}.mlp.gate_proj", # qwen3-embedding
+ "model.layers.{bid}.mlp.language_mlp.gate_proj", # cogvlm
),
MODEL_TENSOR.FFN_GATE_EXP: (
"model.transformer.blocks.{bid}.ff_out", # llada
"layers.{bid}.mlp.down_proj", # qwen3-embedding
"backbone.layers.{bid}.mixer.down_proj", # nemotron-h
+ "model.layers.{bid}.mlp.language_mlp.down_proj", # cogvlm
),
MODEL_TENSOR.FFN_DOWN_EXP: (
"encoder.block.{bid}.layer.1.DenseReluDense.wo", # t5
),
+ MODEL_TENSOR.VISEXP_UP: (
+ "model.layers.{bid}.mlp.vision_mlp.up_proj", # cogvlm
+ ),
+
+ MODEL_TENSOR.VISEXP_GATE: (
+ "model.layers.{bid}.mlp.vision_mlp.gate_proj", # cogvlm
+ ),
+
+ MODEL_TENSOR.VISEXP_DOWN: (
+ "model.layers.{bid}.mlp.vision_mlp.down_proj", # cogvlm
+ ),
+
+ MODEL_TENSOR.VISEXP_ATTN_OUT: (
+ "model.layers.{bid}.self_attn.vision_expert_dense", # cogvlm
+ ),
+
+ MODEL_TENSOR.VISEXP_ATTN_QKV: (
+ "model.layers.{bid}.self_attn.vision_expert_query_key_value", # cogvlm
+ ),
+
############################################################################
# TODO: these do not belong to block_mappings_cfg - move them to mappings_cfg
MODEL_TENSOR.ENC_OUTPUT_NORM: (
MODEL_TENSOR.V_MMPROJ_FC: (
"model.connector.modality_projection.proj", # SmolVLM
+ "model.vision.linear_proj.linear_proj", # cogvlm
),
MODEL_TENSOR.V_MMPROJ_MLP: (
"vision_tower.vision_model.embeddings.class_embedding",
"model.vision_tower.embeddings.cls_token", # Intern-S1
"vision_model.class_embedding", # llama 4
+ "model.vision.patch_embedding.cls_embedding", # cogvlm
),
MODEL_TENSOR.V_ENC_EMBD_PATCH: (
"vision_model.patch_embedding.linear", # llama 4
"visual.patch_embed.proj", # qwen2vl
"vision_tower.patch_embed.proj", # kimi-vl
+ "model.vision.patch_embedding.proj", # cogvlm
),
MODEL_TENSOR.V_ENC_EMBD_POS: (
"model.vision_model.embeddings.position_embedding", # SmolVLM
"vision_model.positional_embedding_vlm", # llama 4
"vision_tower.patch_embed.pos_emb", # kimi-vl
+ "model.vision.patch_embedding.position_embedding", # cogvlm
+ ),
+
+ MODEL_TENSOR.V_ENC_ATTN_QKV: (
+ "model.vision.transformer.layers.{bid}.attention.query_key_value", # cogvlm
),
MODEL_TENSOR.V_ENC_ATTN_Q: (
"vision_model.model.layers.{bid}.input_layernorm", # llama4
"visual.blocks.{bid}.norm1", # qwen2vl
"vision_tower.encoder.blocks.{bid}.norm0", # kimi-vl (norm0/norm1)
+ "model.vision.transformer.layers.{bid}.input_layernorm", # cogvlm
),
MODEL_TENSOR.V_ENC_ATTN_O: (
"vision_encoder.transformer.layers.{bid}.attention.wo", # pixtral
"visual.blocks.{bid}.attn.proj", # qwen2vl
"vision_tower.encoder.blocks.{bid}.wo", # kimi-vl
+ "model.vision.transformer.layers.{bid}.attention.dense", # cogvlm
),
MODEL_TENSOR.V_ENC_POST_ATTN_NORM: (
"vision_encoder.transformer.layers.{bid}.ffn_norm", # pixtral
"visual.blocks.{bid}.norm2", # qwen2vl
"vision_tower.encoder.blocks.{bid}.norm1", # kimi-vl (norm0/norm1)
+ "model.vision.transformer.layers.{bid}.post_attention_layernorm", # cogvlm
),
MODEL_TENSOR.V_ENC_FFN_UP: (
"visual.blocks.{bid}.mlp.fc1", # qwen2vl
"visual.blocks.{bid}.mlp.up_proj", # qwen2.5vl
"vision_tower.encoder.blocks.{bid}.mlp.fc0", # kimi-vl (fc0/fc1)
+ "model.vision.transformer.layers.{bid}.mlp.fc1", # cogvlm
),
MODEL_TENSOR.V_ENC_FFN_GATE: (
"visual.blocks.{bid}.mlp.fc2", # qwen2vl
"visual.blocks.{bid}.mlp.down_proj", # qwen2.5vl
"vision_tower.encoder.blocks.{bid}.mlp.fc1", # kimi-vl (fc0/fc1)
+ "model.vision.transformer.layers.{bid}.mlp.fc2", # cogvlm
),
MODEL_TENSOR.V_LAYER_SCALE_1: (
"multi_modal_projector.layer_norm",
"multi_modal_projector.pre_norm",
"pre_mm_projector_norm",
+ "model.vision.linear_proj.norm1", # cogvlm
),
MODEL_TENSOR.V_MM_SOFT_EMB_NORM: (
"patch_merger.merging_layer", # mistral
),
+ MODEL_TENSOR.V_MM_POST_FC_NORM: (
+ "model.vision.linear_proj.norm1", # cogvlm
+ ),
+
+ MODEL_TENSOR.V_MM_UP: (
+ "model.vision.linear_proj.dense_h_to_4h", # cogvlm
+ ),
+
+ MODEL_TENSOR.V_MM_DOWN: (
+ "model.vision.linear_proj.dense_4h_to_h", # cogvlm
+ ),
+
+ MODEL_TENSOR.V_MM_GATE: (
+ "model.vision.linear_proj.gate_proj", # cogvlm
+ ),
+
+ MODEL_TENSOR.V_TOK_BOI: (
+ "model.vision.boi", # cogvlm
+ ),
+
+ MODEL_TENSOR.V_TOK_EOI: (
+ "model.vision.eoi", # cogvlm
+ ),
+
# audio (mtmd)
MODEL_TENSOR.A_ENC_EMBD_POS: (
{ LLM_ARCH_SEED_OSS, "seed_oss" },
{ LLM_ARCH_GROVEMOE, "grovemoe" },
{ LLM_ARCH_APERTUS, "apertus" },
+ { LLM_ARCH_COGVLM, "cogvlm" },
{ LLM_ARCH_UNKNOWN, "(unknown)" },
};
{ LLM_TENSOR_FFN_UP_CHEXPS, "blk.%d.ffn_up_chexps" },
},
},
+ {
+ LLM_ARCH_COGVLM,
+ {
+ { LLM_TENSOR_TOKEN_EMBD, "token_embd" },
+ { LLM_TENSOR_OUTPUT_NORM, "output_norm" },
+ { LLM_TENSOR_OUTPUT, "output" },
+ { LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
+ { LLM_TENSOR_ATTN_QKV, "blk.%d.attn_qkv" },
+ { LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
+ { LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
+ { LLM_TENSOR_FFN_GATE, "blk.%d.ffn_gate" },
+ { LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
+ { LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
+ { LLM_TENSOR_VISEXP_ATTN_QKV, "blk.%d.vis_attn_qkv" },
+ { LLM_TENSOR_VISEXP_ATTN_OUT, "blk.%d.vis_attn_output" },
+ { LLM_TENSOR_VISEXP_FFN_GATE, "blk.%d.vis_gate" },
+ { LLM_TENSOR_VISEXP_FFN_DOWN, "blk.%d.vis_down" },
+ { LLM_TENSOR_VISEXP_FFN_UP, "blk.%d.vis_up" },
+ },
+ },
{
LLM_ARCH_UNKNOWN,
{
{LLM_TENSOR_SHORTCONV_CONV, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_SSM_CONV}},
{LLM_TENSOR_SHORTCONV_INPROJ, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
{LLM_TENSOR_SHORTCONV_OUTPROJ, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
+ {LLM_TENSOR_VISEXP_ATTN_QKV, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
+ {LLM_TENSOR_VISEXP_ATTN_OUT, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
+ {LLM_TENSOR_VISEXP_FFN_GATE, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
+ {LLM_TENSOR_VISEXP_FFN_DOWN, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
+ {LLM_TENSOR_VISEXP_FFN_UP, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
// NextN/MTP tensors are currently ignored (reserved for future MTP support)
// These tensors only exist in the last layer(s) and are treated as output tensors
{LLM_TENSOR_NEXTN_EH_PROJ, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL_MAT}},
LLM_ARCH_SEED_OSS,
LLM_ARCH_GROVEMOE,
LLM_ARCH_APERTUS,
+ LLM_ARCH_COGVLM,
LLM_ARCH_UNKNOWN,
};
LLM_TENSOR_SHORTCONV_CONV,
LLM_TENSOR_SHORTCONV_INPROJ,
LLM_TENSOR_SHORTCONV_OUTPROJ,
+ LLM_TENSOR_VISEXP_ATTN_QKV,
+ LLM_TENSOR_VISEXP_ATTN_OUT,
+ LLM_TENSOR_VISEXP_FFN_GATE,
+ LLM_TENSOR_VISEXP_FFN_DOWN,
+ LLM_TENSOR_VISEXP_FFN_UP,
LLM_TENSOR_NEXTN_EH_PROJ,
LLM_TENSOR_NEXTN_EMBED_TOKENS,
LLM_TENSOR_NEXTN_ENORM,
default: type = LLM_TYPE_UNKNOWN;
}
} break;
+ case LLM_ARCH_COGVLM:
+ {
+ ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
+ switch (hparams.n_layer) {
+ case 32: type = LLM_TYPE_13B; break;
+ default: type = LLM_TYPE_UNKNOWN;
+ }
+ } break;
default: throw std::runtime_error("unsupported model architecture");
}
layer.attn_k_norm_b = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "bias", i), { n_embd_head_k }, TENSOR_NOT_REQUIRED);
}
} break;
+ case LLM_ARCH_COGVLM:
+ {
+ tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
+
+ // output
+ output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
+ output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
+
+ // if output is NULL, init from the input tok embed
+ if (output == NULL) {
+ output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
+ }
+
+ for (int i = 0; i < n_layer; ++i) {
+ auto & layer = layers[i];
+
+ layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
+ layer.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd_head_k * n_head * 3}, 0);
+ layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
+
+ layer.visexp_attn_wqkv = create_tensor(tn(LLM_TENSOR_VISEXP_ATTN_QKV, "weight", i), {n_embd, n_embd_head_k * n_head * 3}, 0);
+ layer.visexp_attn_wo = create_tensor(tn(LLM_TENSOR_VISEXP_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
+
+ layer.rope_freqs = create_tensor(tn(LLM_TENSOR_ROPE_FREQS, "weight", i), {n_rot/2}, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
+
+ layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
+ layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
+ layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}, 0);
+ layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
+
+ layer.visexp_ffn_gate = create_tensor(tn(LLM_TENSOR_VISEXP_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
+ layer.visexp_ffn_down = create_tensor(tn(LLM_TENSOR_VISEXP_FFN_DOWN, "weight", i), { n_ff, n_embd}, 0);
+ layer.visexp_ffn_up = create_tensor(tn(LLM_TENSOR_VISEXP_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
+ }
+ } break;
default:
throw std::runtime_error("unknown architecture");
}
}
};
+struct llm_build_cogvlm : public llm_graph_context {
+ llm_build_cogvlm(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
+ const int64_t n_embd_head = hparams.n_embd_head_v;
+ float kq_scale = 1.0f / sqrtf(float(n_embd_head));
+
+ GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
+ GGML_ASSERT(n_embd_head == hparams.n_rot);
+
+ ggml_tensor * inpL, * cur;
+ inpL = build_inp_embd(model.tok_embd);
+
+ ggml_tensor * inp_pos = build_inp_pos();
+
+ auto * inp_attn = build_attn_inp_kv();
+
+ // check ubatch to see if we have input tokens (text)
+ // or an input embedding vector (image)
+ bool is_text;
+ if (ubatch.token) {
+ is_text = true;
+ } else {
+ is_text = false;
+ }
+
+ for (int il = 0; il < n_layer; ++il) {
+ // get either the text or image weight tensors
+ ggml_tensor * wqkv, * wo;
+ ggml_tensor * ffn_gate, * ffn_down, * ffn_up;
+
+ if (is_text) {
+ wqkv = model.layers[il].wqkv;
+ wo = model.layers[il].wo;
+ ffn_gate = model.layers[il].ffn_gate;
+ ffn_down = model.layers[il].ffn_down;
+ ffn_up = model.layers[il].ffn_up;
+ } else {
+ wqkv = model.layers[il].visexp_attn_wqkv;
+ wo = model.layers[il].visexp_attn_wo;
+ ffn_gate = model.layers[il].visexp_ffn_gate;
+ ffn_down = model.layers[il].visexp_ffn_down;
+ ffn_up = model.layers[il].visexp_ffn_up;
+ }
+
+ ggml_tensor * inpSA = inpL;
+ cur = build_norm(inpSA, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
+
+ // build self attention
+ {
+ ggml_tensor * qkv = build_lora_mm(wqkv, cur);
+
+ // split qkv into Q, K, V along the first dimension
+ ggml_tensor * Qcur = ggml_view_3d(ctx0, qkv, n_embd_head, n_head, n_tokens, n_embd_head * sizeof(float),
+ qkv->nb[1], 0);
+ ggml_tensor * Kcur = ggml_view_3d(ctx0, qkv, n_embd_head, n_head_kv, n_tokens, n_embd_head * sizeof(float),
+ qkv->nb[1], n_embd * ggml_element_size(qkv));
+ ggml_tensor * Vcur = ggml_view_3d(ctx0, qkv, n_embd_head, n_head_kv, n_tokens, n_embd_head * sizeof(float),
+ qkv->nb[1], 2 * n_embd * ggml_element_size(qkv));
+
+ Qcur = ggml_rope(ctx0, Qcur, inp_pos, n_embd_head, rope_type);
+ Kcur = ggml_rope(ctx0, Kcur, inp_pos, n_embd_head, rope_type);
+
+ cur = build_attn(inp_attn, wo, nullptr, Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
+ cb(cur, "attn_out", il);
+ }
+
+ ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
+ cb(ffn_inp, "ffn_inp", il);
+
+ cur = build_norm(ffn_inp, model.layers[il].ffn_norm, NULL, LLM_NORM_RMS, il);
+ cb(cur, "ffn_norm", il);
+
+ cur = build_ffn(cur,
+ ffn_up, NULL, NULL,
+ ffn_gate, NULL, NULL,
+ ffn_down, NULL, NULL,
+ NULL,
+ LLM_FFN_SILU, LLM_FFN_PAR, il);
+
+ cur = ggml_add(ctx0, cur, ffn_inp);
+ cb(cur, "ffn_out", il);
+
+ inpL = cur;
+ }
+
+ cur = inpL;
+
+ cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);
+ cb(cur, "result_norm", -1);
+ res->t_embd = cur;
+
+ cur = build_lora_mm(model.output, cur);
+ cb(cur, "result_output", -1);
+ res->t_logits = cur;
+ ggml_build_forward_expand(gf, cur);
+
+ }
+};
+
llama_memory_i * llama_model::create_memory(const llama_memory_params & params, const llama_cparams & cparams) const {
llama_memory_i * res;
{
llm = std::make_unique<llm_build_apertus>(*this, params);
} break;
+ case LLM_ARCH_COGVLM:
+ {
+ llm = std::make_unique<llm_build_cogvlm>(*this, params);
+ } break;
default:
GGML_ABORT("fatal error");
}
case LLM_ARCH_SEED_OSS:
case LLM_ARCH_GROVEMOE:
case LLM_ARCH_APERTUS:
+ case LLM_ARCH_COGVLM:
return LLAMA_ROPE_TYPE_NEOX;
case LLM_ARCH_QWEN2VL:
// openai-moe
struct ggml_tensor * attn_sinks = nullptr;
+ // cogvlm
+ struct ggml_tensor * visexp_attn_wqkv = nullptr;
+ struct ggml_tensor * visexp_attn_wo = nullptr;
+ struct ggml_tensor * visexp_ffn_gate = nullptr;
+ struct ggml_tensor * visexp_ffn_down = nullptr;
+ struct ggml_tensor * visexp_ffn_up = nullptr;
+
// xIELU activation parameters for Apertus
struct ggml_tensor * ffn_act_alpha_n = nullptr;
struct ggml_tensor * ffn_act_alpha_p = nullptr;
#define TN_PATCH_EMBD "v.patch_embd.weight" // not rename tensor with ".0" postfix for backwrad compat
#define TN_PATCH_EMBD_1 "v.patch_embd.weight.1"
#define TN_PATCH_BIAS "v.patch_embd.bias"
+#define TN_ATTN_QKV "%s.blk.%d.attn_qkv.%s"
#define TN_ATTN_K "%s.blk.%d.attn_k.%s"
#define TN_ATTN_Q "%s.blk.%d.attn_q.%s"
#define TN_ATTN_V "%s.blk.%d.attn_v.%s"
#define TN_MM_NORM_PRE "mm.a.norm_pre.%s"
#define TN_MM_NORM_MID "mm.a.norm_mid.%s"
+// cogvlm
+#define TN_MM_POST_FC_NORM "mm.post_fc_norm.%s"
+#define TN_MM_H_TO_4H "mm.up.%s"
+#define TN_MM_GATE "mm.gate.%s"
+#define TN_MM_4H_TO_H "mm.down.%s"
+#define TN_TOK_BOI "v.boi"
+#define TN_TOK_EOI "v.eoi"
+
// align x to upper multiple of n
#define CLIP_ALIGN(x, n) ((((x) + (n) - 1) / (n)) * (n))
PROJECTOR_TYPE_KIMIVL,
PROJECTOR_TYPE_LIGHTONOCR,
PROJECTOR_TYPE_UNKNOWN,
+ PROJECTOR_TYPE_COGVLM,
};
static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
{ PROJECTOR_TYPE_LFM2, "lfm2"},
{ PROJECTOR_TYPE_KIMIVL, "kimivl"},
{ PROJECTOR_TYPE_LIGHTONOCR,"lightonocr"},
+ { PROJECTOR_TYPE_COGVLM, "cogvlm"},
};
static projector_type clip_projector_type_from_string(const std::string & str) {
ggml_tensor * q_b = nullptr;
ggml_tensor * v_w = nullptr;
ggml_tensor * v_b = nullptr;
+ ggml_tensor * qkv_w = nullptr;
+ ggml_tensor * qkv_b = nullptr;
ggml_tensor * o_w = nullptr;
ggml_tensor * o_b = nullptr;
// GLMV-Edge projection
ggml_tensor * mm_model_adapter_conv_w = nullptr;
ggml_tensor * mm_model_adapter_conv_b = nullptr;
- ggml_tensor * mm_glm_tok_boi = nullptr;
- ggml_tensor * mm_glm_tok_eoi = nullptr;
// MobileVLM projection
ggml_tensor * mm_model_mlp_1_w = nullptr;
ggml_tensor * mm_norm_pre_w = nullptr;
ggml_tensor * mm_norm_mid_w = nullptr;
+ // cogvlm
+ ggml_tensor * mm_post_fc_norm_w = nullptr;
+ ggml_tensor * mm_post_fc_norm_b = nullptr;
+ ggml_tensor * mm_h_to_4h_w = nullptr;
+ ggml_tensor * mm_gate_w = nullptr;
+ ggml_tensor * mm_4h_to_h_w = nullptr;
+ ggml_tensor * mm_boi = nullptr;
+ ggml_tensor * mm_eoi = nullptr;
+
bool audio_has_avgpool() const {
return proj_type == PROJECTOR_TYPE_QWEN2A
|| proj_type == PROJECTOR_TYPE_VOXTRAL;
// note: these embeddings are not present in text model, hence we cannot process them as text tokens
// see: https://huggingface.co/THUDM/glm-edge-v-2b/blob/main/siglip.py#L53
{
- embeddings = ggml_concat(ctx0, model.mm_glm_tok_boi, embeddings, 1); // BOI
- embeddings = ggml_concat(ctx0, embeddings, model.mm_glm_tok_eoi, 1); // EOI
+ embeddings = ggml_concat(ctx0, model.mm_boi, embeddings, 1); // BOI
+ embeddings = ggml_concat(ctx0, embeddings, model.mm_eoi, 1); // EOI
}
}
return gf;
}
+ // cogvlm vision encoder
+ ggml_cgraph * build_cogvlm() {
+ GGML_ASSERT(model.class_embedding != nullptr);
+ GGML_ASSERT(model.position_embeddings != nullptr);
+
+ const int n_pos = n_patches + 1; // +1 for [CLS]
+
+ // build input and concatenate class embedding
+ ggml_tensor * inp = build_inp();
+ inp = ggml_concat(ctx0, inp, model.class_embedding, 1);
+
+ inp = ggml_add(ctx0, inp, model.position_embeddings);
+ cb(inp, "inp_pos", -1);
+
+ ggml_tensor * inpL = inp;
+
+ for (int il = 0; il < n_layer; il++) {
+ auto & layer = model.layers[il];
+ ggml_tensor * cur = inpL;
+
+ cur = ggml_mul_mat(ctx0, layer.qkv_w, cur);
+
+ cur = ggml_add(ctx0, cur, layer.qkv_b);
+
+ ggml_tensor * Qcur = ggml_view_3d(ctx0, cur, d_head, n_head, n_pos, d_head*sizeof(float),
+ cur->nb[1], 0);
+ ggml_tensor * Kcur = ggml_view_3d(ctx0, cur, d_head, n_head, n_pos, d_head*sizeof(float),
+ cur->nb[1], n_embd * sizeof(float));
+ ggml_tensor * Vcur = ggml_view_3d(ctx0, cur, d_head, n_head, n_pos, d_head*sizeof(float),
+ cur->nb[1], 2 * n_embd * sizeof(float));
+
+ cb(Qcur, "Qcur", il);
+ cb(Kcur, "Kcur", il);
+ cb(Vcur, "Vcur", il);
+
+ cur = build_attn(layer.o_w, layer.o_b,
+ Qcur, Kcur, Vcur, nullptr, kq_scale, il);
+ cb(cur, "attn_out", il);
+
+ cur = build_norm(cur, layer.ln_1_w, layer.ln_1_b, NORM_TYPE_NORMAL, eps, il);
+ cb(cur, "attn_post_norm", il);
+
+ cur = ggml_add(ctx0, cur, inpL);
+ inpL = cur;
+
+ cur = build_ffn(cur,
+ layer.ff_up_w, layer.ff_up_b,
+ layer.ff_gate_w, layer.ff_gate_b,
+ layer.ff_down_w, layer.ff_down_b,
+ hparams.ffn_op, il);
+
+ cb(cur, "ffn_out", il);
+
+ cur = build_norm(cur, layer.ln_2_w, layer.ln_2_b, NORM_TYPE_NORMAL, eps, il);
+ cb(cur, "ffn_post_norm", il);
+
+ cur = ggml_add(ctx0, cur, inpL);
+ cb(cur, "layer_out", il);
+ inpL = cur;
+
+ }
+
+ // remove CLS token (like build_llama4 does)
+ ggml_tensor * cur = ggml_view_2d(ctx0, inpL,
+ n_embd, n_patches,
+ ggml_row_size(inpL->type, n_embd), 0);
+
+ // Multiply with mm_model_proj
+ cur = ggml_mul_mat(ctx0, model.mm_model_proj, cur);
+
+ // Apply layernorm, weight, bias
+ cur = build_norm(cur, model.mm_post_fc_norm_w, model.mm_post_fc_norm_b, NORM_TYPE_NORMAL, 1e-5, -1);
+
+ // Apply GELU
+ cur = ggml_gelu_inplace(ctx0, cur);
+
+ // Branch 1: multiply with mm_h_to_4h_w
+ ggml_tensor * h_to_4h = ggml_mul_mat(ctx0, model.mm_h_to_4h_w, cur);
+
+ // Branch 2: multiply with mm_gate_w
+ ggml_tensor * gate = ggml_mul_mat(ctx0, model.mm_gate_w, cur);
+
+ // Apply silu
+ gate = ggml_swiglu_split(ctx0, gate, h_to_4h);
+
+ // Apply mm_4h_to_h_w
+ cur = ggml_mul_mat(ctx0, model.mm_4h_to_h_w, gate);
+
+ // Concatenate with boi and eoi
+ cur = ggml_concat(ctx0, model.mm_boi, cur, 1);
+ cur = ggml_concat(ctx0, cur, model.mm_eoi, 1);
+
+ // build the graph
+ ggml_build_forward_expand(gf, cur);
+
+ return gf;
+ }
+
private:
//
// utility functions
{
res = graph.build_kimivl();
} break;
+ case PROJECTOR_TYPE_COGVLM:
+ {
+ res = graph.build_cogvlm();
+ } break;
default:
{
res = graph.build_llava();
model.layers.resize(hparams.n_layer);
for (int il = 0; il < hparams.n_layer; ++il) {
auto & layer = model.layers[il];
- layer.k_w = get_tensor(string_format(TN_ATTN_K, prefix, il, "weight"));
- layer.q_w = get_tensor(string_format(TN_ATTN_Q, prefix, il, "weight"));
- layer.v_w = get_tensor(string_format(TN_ATTN_V, prefix, il, "weight"));
+ layer.k_w = get_tensor(string_format(TN_ATTN_K, prefix, il, "weight"), false);
+ layer.q_w = get_tensor(string_format(TN_ATTN_Q, prefix, il, "weight"), false);
+ layer.v_w = get_tensor(string_format(TN_ATTN_V, prefix, il, "weight"), false);
layer.o_w = get_tensor(string_format(TN_ATTN_OUTPUT, prefix, il, "weight"));
+ layer.qkv_w = get_tensor(string_format(TN_ATTN_QKV, prefix, il, "weight"), false);
layer.k_norm = get_tensor(string_format(TN_ATTN_K_NORM, prefix, il, "weight"), false);
layer.q_norm = get_tensor(string_format(TN_ATTN_Q_NORM, prefix, il, "weight"), false);
layer.ln_1_w = get_tensor(string_format(TN_LN_1, prefix, il, "weight"), false);
layer.q_b = get_tensor(string_format(TN_ATTN_Q, prefix, il, "bias"), false);
layer.v_b = get_tensor(string_format(TN_ATTN_V, prefix, il, "bias"), false);
layer.o_b = get_tensor(string_format(TN_ATTN_OUTPUT, prefix, il, "bias"), false);
+ layer.qkv_b = get_tensor(string_format(TN_ATTN_QKV, prefix, il, "bias"), false);
layer.ln_1_b = get_tensor(string_format(TN_LN_1, prefix, il, "bias"), false);
layer.ln_2_b = get_tensor(string_format(TN_LN_2, prefix, il, "bias"), false);
model.mm_model_mlp_1_w = get_tensor(string_format(TN_GLM_ADAPTER_D_H_2_4H, "weight"));
model.mm_model_mlp_2_w = get_tensor(string_format(TN_GLM_ADAPTER_GATE, "weight"));
model.mm_model_mlp_3_w = get_tensor(string_format(TN_GLM_ADAPTER_D_4H_2_H, "weight"));
- model.mm_glm_tok_boi = get_tensor(string_format(TN_TOK_GLM_BOI, "weight"));
- model.mm_glm_tok_eoi = get_tensor(string_format(TN_TOK_GLM_EOI, "weight"));
+ model.mm_boi = get_tensor(string_format(TN_TOK_GLM_BOI, "weight"));
+ model.mm_eoi = get_tensor(string_format(TN_TOK_GLM_EOI, "weight"));
} break;
case PROJECTOR_TYPE_QWEN2VL:
case PROJECTOR_TYPE_QWEN25VL:
model.mm_model_mlp_1_w = get_tensor(string_format(TN_MVLM_PROJ_MLP, 1, "weight"));
model.mm_model_mlp_2_w = get_tensor(string_format(TN_MVLM_PROJ_MLP, 2, "weight"));
} break;
+ case PROJECTOR_TYPE_COGVLM:
+ {
+ model.mm_model_proj = get_tensor(TN_MM_PROJECTOR);
+ model.mm_post_fc_norm_w = get_tensor(string_format(TN_MM_POST_FC_NORM, "weight"));
+ model.mm_post_fc_norm_b = get_tensor(string_format(TN_MM_POST_FC_NORM, "bias"));
+ model.mm_h_to_4h_w = get_tensor(string_format(TN_MM_H_TO_4H, "weight"));
+ model.mm_gate_w = get_tensor(string_format(TN_MM_GATE, "weight"));
+ model.mm_4h_to_h_w = get_tensor(string_format(TN_MM_4H_TO_H, "weight"));
+ model.mm_boi = get_tensor(TN_TOK_BOI);
+ model.mm_eoi = get_tensor(TN_TOK_EOI);
+ } break;
default:
GGML_ASSERT(false && "unknown projector type");
}
case PROJECTOR_TYPE_GLM_EDGE:
{
n_patches /= 4;
- if (ctx->model.mm_glm_tok_boi) {
+ if (ctx->model.mm_boi) {
n_patches += 2; // for BOI and EOI token embeddings
}
} break;
n_patches /= 2;
}
} break;
+ case PROJECTOR_TYPE_COGVLM:
+ {
+ n_patches += 2; // for BOI and EOI token embeddings
+ } break;
default:
GGML_ABORT("unsupported projector type");
}
case PROJECTOR_TYPE_ULTRAVOX:
case PROJECTOR_TYPE_LFM2:
case PROJECTOR_TYPE_VOXTRAL:
+ case PROJECTOR_TYPE_COGVLM:
{
// do nothing
} break;
case PROJECTOR_TYPE_LFM2:
case PROJECTOR_TYPE_KIMIVL:
return ctx->model.mm_2_w->ne[1];
+ case PROJECTOR_TYPE_COGVLM:
+ return ctx->model.mm_4h_to_h_w->ne[1];
default:
GGML_ABORT("Unknown projector type");
}
overview / pkg / ggml / sources / llama.cpp / commitdiff