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

llama : add support for BitnetForCausalLM (#7931)

Browse source 
* hf bitnet v1

* hf bitnet e2e v2

* finish bitnet e2e

* finish f16 hf bitnet e2e

* remove unsed

* finish bitnet i2 e2e

* move i2s to quantize v1

* move i2 to quantize

* clean code

* clean code 2

* fix codestyle

* fix code

* fix

* fix code

* fix merge

* remove unused

* change table name

* fix whitespace

* delete redundant

* i2_s to absmax

* finish i2_s/i8_s vec_dot x86 simd

* i2s->q22

* fix code

* remove block scale

* add dequantize

* fix seq

* update avx2

* remove q2_2

* remove q22_grid

* fix whitespace

* reuse llm_build_kv

* fix bo

---------

Co-authored-by: root <root@wangjinheng>
This commit is contained in:
Eddie-Wang 2024-06-24 02:27:57 +08:00 • committed by GitHub
parent 6a2f298bd7
commit e112b610a1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 307 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

21
gguf-py/gguf/constants.py
View file

@ -149,6 +149,7 @@ class MODEL_ARCH(IntEnum):
OLMO = auto()
ARCTIC = auto()
DEEPSEEK2 = auto()
BITNET = auto()
class MODEL_TENSOR(IntEnum):
@ -200,6 +201,8 @@ class MODEL_TENSOR(IntEnum):
ATTN_KV_B = auto()
ATTN_Q_A_NORM = auto()
ATTN_KV_A_NORM = auto()
FFN_SUB_NORM = auto()
ATTN_SUB_NORM = auto()
MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
@ -237,6 +240,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.OLMO: "olmo",
MODEL_ARCH.ARCTIC: "arctic",
MODEL_ARCH.DEEPSEEK2: "deepseek2",
MODEL_ARCH.BITNET: "bitnet",
}
TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
@ -288,6 +292,8 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
MODEL_TENSOR.ATTN_KV_B: "blk.{bid}.attn_kv_b",
MODEL_TENSOR.ATTN_Q_A_NORM: "blk.{bid}.attn_q_a_norm",
MODEL_TENSOR.ATTN_KV_A_NORM: "blk.{bid}.attn_kv_a_norm",
MODEL_TENSOR.ATTN_SUB_NORM: "blk.{bid}.attn_sub_norm",
MODEL_TENSOR.FFN_SUB_NORM: "blk.{bid}.ffn_sub_norm",
}
MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
@ -808,6 +814,21 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN_SHEXP,
MODEL_TENSOR.FFN_UP_SHEXP,
],
MODEL_ARCH.BITNET: [
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.ATTN_SUB_NORM,
MODEL_TENSOR.FFN_SUB_NORM,
],
# TODO
}