CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-21 12:16:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : add AfmoeForCausalLM support (#16477)

Browse Source 
* Add AFMOE model support

* Update to vocab

* Add model sizing

* Undo Rope change for ARCEE model

* Address review comments

* Update modeling code is_sliding -> use_rope, replace hard-coded logic

* Fix AFMOE tokenizer

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update AFMoE tokenizer class identification to be more unique

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Bartowski
2025-11-14 07:54:10 -05:00
committed by GitHub
parent 6cd0cf72ce
commit e1fcf8b09b
14 changed files with 541 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-model.h
View File

@@ -76,6 +76,7 @@ enum llm_type {
LLM_TYPE_15B,
LLM_TYPE_16B,
LLM_TYPE_20B,
LLM_TYPE_26B,
LLM_TYPE_27B,
LLM_TYPE_30B,
LLM_TYPE_32B,
@@ -234,6 +235,7 @@ struct llama_layer {
struct ggml_tensor * wk_enc = nullptr;
struct ggml_tensor * wv_enc = nullptr;
struct ggml_tensor * wo_enc = nullptr;
struct ggml_tensor * wqkv_gate = nullptr;
// attention bias
struct ggml_tensor * bq = nullptr;