CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : add NeoBERT (#14164)

Browse Source 
* convert neobert model to gguf

* add inference graph

* fix flake8 lint

* followed reviewer suggestions

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* follow reviewers suggestions

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* override NeoBERT feed-forward length

---------

Co-authored-by: dinhhuy <huy.dinh@brains-tech.co.jp>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Đinh Trọng Huy
2025-06-16 21:53:41 +09:00
committed by GitHub
parent 7d6d91babf
commit ad590be98c
6 changed files with 222 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/llama-arch.cpp
View File

@@ -20,6 +20,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_BERT, "bert" },
{ LLM_ARCH_NOMIC_BERT, "nomic-bert" },
{ LLM_ARCH_NOMIC_BERT_MOE, "nomic-bert-moe" },
{ LLM_ARCH_NEO_BERT, "neo-bert" },
{ LLM_ARCH_JINA_BERT_V2, "jina-bert-v2" },
{ LLM_ARCH_BLOOM, "bloom" },
{ LLM_ARCH_STABLELM, "stablelm" },
@@ -514,6 +515,21 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_FFN_UP_EXPS, "blk.%d.ffn_up_exps" },
},
},
{
LLM_ARCH_NEO_BERT,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ 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_DOWN, "blk.%d.ffn_down" },
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
{ LLM_TENSOR_ENC_OUTPUT_NORM, "enc.output_norm" },
{ LLM_TENSOR_CLS, "cls" },
{ LLM_TENSOR_CLS_OUT, "cls.output" },
},
},
{
LLM_ARCH_JINA_BERT_V2,
{