CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-15 11:17:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

model: Add support for CogVLM model (#15002)

Browse Source 
* 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 <son@huggingface.co>
This commit is contained in:
Tianyue-Zhao
2025-10-30 07:18:50 -04:00
committed by GitHub
parent 229bf68628
commit bacddc049a
9 changed files with 501 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tools/mtmd/clip-impl.h
View File

@@ -63,6 +63,7 @@
#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"
@@ -116,6 +117,14 @@
#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))
@@ -141,6 +150,7 @@ enum projector_type {
PROJECTOR_TYPE_KIMIVL,
PROJECTOR_TYPE_LIGHTONOCR,
PROJECTOR_TYPE_UNKNOWN,
PROJECTOR_TYPE_COGVLM,
};
static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
@@ -163,6 +173,7 @@ 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) {