vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add Jina Embeddings architecture (#6826)

Browse source 
* feat: first things to do

* feat: create tensors for Jina architecture

* fix: use other tensors

* feat: embedding gets results

* fix: fix usage of ALIBI

* fix: clean prints

* fix: do some cleanup unused vars

* fix: revert changes to Makefile and CMakeLists

* fix: revert some changes

* fix: fix small detail

* fix: fix convert formatting

* fix: fix linting and editor

* feat: set proper vocab settings

* fix: JinaBertForMaskedLM registration

* feat: support q_normalization and k_normalization in Jina arch

* feat: handle gpt2 tokenizer with Jina architecture

* feat: example comments in embedding

* feat: rename Jina Bert to Jina Bert V2

* fix: add some changes as per review

* feat: proper KQ_pos for Jina embeddings

* feat: add capacity to load models ES and DE for Spanish

* llama : fix pre-tokenizers

* ggml : full ALiBi support

* ggml : update ggml_soft_max_ext() CUDA, SYCL

* ggml : ggml_flash_attn_ext() support ALiBi (CPU)

* ggml : ggml_flash_attn_ext() support ALiBi (Metal)

* ggml : fix warning

* ggml : ggml_flash_attn_ext() support ALiBi (CUDA)

ggml-ci

* minor : clean-up

* embedding : add warning about missing SEP

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Joan Fontanals 2024-05-11 09:46:09 +02:00 • committed by GitHub
parent 9cb317f77e
commit b83cc3f5b3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 236 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

18
gguf-py/gguf/constants.py
View file

@ -118,6 +118,7 @@ class MODEL_ARCH(IntEnum):
REFACT = auto()
BERT = auto()
NOMIC_BERT = auto()
JINA_BERT_V2 = auto()
BLOOM = auto()
STABLELM = auto()
QWEN = auto()
@ -195,6 +196,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.REFACT: "refact",
MODEL_ARCH.BERT: "bert",
MODEL_ARCH.NOMIC_BERT: "nomic-bert",
MODEL_ARCH.JINA_BERT_V2: "jina-bert-v2",
MODEL_ARCH.BLOOM: "bloom",
MODEL_ARCH.STABLELM: "stablelm",
MODEL_ARCH.QWEN: "qwen",
@ -380,6 +382,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.LAYER_OUT_NORM,
],
MODEL_ARCH.JINA_BERT_V2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.TOKEN_EMBD_NORM,
MODEL_TENSOR.TOKEN_TYPES,
MODEL_TENSOR.ATTN_OUT_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.LAYER_OUT_NORM,
],
MODEL_ARCH.MPT: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,

6
gguf-py/gguf/tensor_mapping.py
View file

@ -243,6 +243,7 @@ class TensorNameMap:
"model.layers.{bid}.feed_forward.w3", # internlm2
"encoder.layers.{bid}.mlp.fc11", # nomic-bert
"model.layers.{bid}.mlp.c_fc", # starcoder2
"encoder.layer.{bid}.mlp.gated_layers_v", # jina-bert-v2
),
MODEL_TENSOR.FFN_UP_EXP: (
@ -269,6 +270,7 @@ class TensorNameMap:
"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
"transformer.h.{bid}.mlp.linear_1", # refact
),
@ -303,6 +305,7 @@ class TensorNameMap:
"model.layers.{bid}.feed_forward.w2", # internlm2
"encoder.layers.{bid}.mlp.fc2", # nomic-bert
"model.layers.{bid}.mlp.c_proj", # starcoder2
"encoder.layer.{bid}.mlp.wo", # jina-bert-v2
),
MODEL_TENSOR.FFN_DOWN_EXP: (
@ -321,6 +324,7 @@ class TensorNameMap:
"model.layers.{bid}.self_attn.q_layernorm", # persimmon
"model.layers.{bid}.self_attn.q_norm", # cohere
"transformer.blocks.{bid}.attn.q_ln", # sea-lion
"encoder.layer.{bid}.attention.self.layer_norm_q" # jina-bert-v2
),
MODEL_TENSOR.ATTN_K_NORM: (
@ -328,6 +332,7 @@ class TensorNameMap:
"model.layers.{bid}.self_attn.k_layernorm", # persimmon
"model.layers.{bid}.self_attn.k_norm", # cohere
"transformer.blocks.{bid}.attn.k_ln", # sea-lion
"encoder.layer.{bid}.attention.self.layer_norm_k" # jina-bert-v2
),
MODEL_TENSOR.ROPE_FREQS: (
@ -338,6 +343,7 @@ class TensorNameMap:
"encoder.layer.{bid}.output.LayerNorm", # bert
"encoder.layers.{bid}.norm2", # nomic-bert
"transformer.decoder_layer.{bid}.rms_norm_3", # Grok
"encoder.layer.{bid}.mlp.layernorm", # jina-bert-v2
),
MODEL_TENSOR.SSM_IN: (