CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : jina-embeddings-v3 support (#13693)

Browse Source 
* initial jina-embeddings-v3 support

* initial jina-embeddings-v3 support

* initial jina-embeddings-v3 support

* fix vocab parsing with only tokenizer.json

* set mask token lstrip attribute

* additional unk_token_id fallback just in case [no ci]

* revert vocab_size() change [no ci]

* merge tensor loading into general bert

* rope

* add lora embedding and loading (non-functional)

* export separate lora ggufs instead

* add adapter metadata api

* use std::string

* convert_hf_to_lora compatibility

* fix assert

* apply suggestions from review

* apply suggestion from review
This commit is contained in:
Sigbjørn Skjæret
2025-08-28 15:49:50 +02:00
committed by GitHub
parent 55042b3692
commit 84ab83cc0b
14 changed files with 245 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
gguf-py/gguf/constants.py
View File

@@ -231,8 +231,10 @@ class Keys:
MIDDLE_ID = "tokenizer.ggml.middle_token_id"
class Adapter:
TYPE = "adapter.type"
LORA_ALPHA = "adapter.lora.alpha"
TYPE = "adapter.type"
LORA_ALPHA = "adapter.lora.alpha"
LORA_TASK_NAME = "adapter.lora.task_name"
LORA_PROMPT_PREFIX = "adapter.lora.prompt_prefix"
class IMatrix:
CHUNK_COUNT = "imatrix.chunk_count"
@@ -315,6 +317,7 @@ class MODEL_ARCH(IntEnum):
NOMIC_BERT_MOE = auto()
NEO_BERT = auto()
JINA_BERT_V2 = auto()
JINA_BERT_V3 = auto()
BLOOM = auto()
STABLELM = auto()
QWEN = auto()
@@ -647,6 +650,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.NOMIC_BERT_MOE: "nomic-bert-moe",
MODEL_ARCH.NEO_BERT: "neo-bert",
MODEL_ARCH.JINA_BERT_V2: "jina-bert-v2",
MODEL_ARCH.JINA_BERT_V3: "jina-bert-v3",
MODEL_ARCH.BLOOM: "bloom",
MODEL_ARCH.STABLELM: "stablelm",
MODEL_ARCH.QWEN: "qwen",
@@ -1234,6 +1238,18 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.LAYER_OUT_NORM,
MODEL_TENSOR.CLS,
],
MODEL_ARCH.JINA_BERT_V3: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.TOKEN_EMBD_NORM,
MODEL_TENSOR.TOKEN_TYPES,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.ATTN_OUT_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.LAYER_OUT_NORM,
],
MODEL_ARCH.MPT: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,