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

[Model] Add support for xverse (#6301)

Browse source 
* Support xverse model convert to gguf format.

* 1. Convert xverse models to gguf;
2. Add LLM_ARCH_XVERSE inference in llama.cpp;
3. Add xverse item in Supported models in README.md;

* * gguf-py: remove redundant logs
* llama: remove the init_mapping_prefetch custom parameter

* llama.cpp: Include the changes from #6122 to exclude the unused outputs of the last layers.

* - Fix format issues
- Remove duplicate set kqv_out to llm_build_kv

* Update llama.cpp

---------

Co-authored-by: willhe <willhe@xverse.cn>
Co-authored-by: willhe <hexin@xverse.cn>
This commit is contained in:
hxer7963 2024-03-29 21:37:03 +08:00 • committed by GitHub
parent cfde806eb9
commit 069574775c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 329 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

22
gguf-py/gguf/constants.py
View file

@ -123,6 +123,7 @@ class MODEL_ARCH(IntEnum):
GEMMA = auto()
STARCODER2 = auto()
MAMBA = auto()
XVERSE = auto()
COMMAND_R = auto()
@ -191,6 +192,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.GEMMA: "gemma",
MODEL_ARCH.STARCODER2: "starcoder2",
MODEL_ARCH.MAMBA: "mamba",
MODEL_ARCH.XVERSE: "xverse",
MODEL_ARCH.COMMAND_R: "command-r",
}
@ -606,6 +608,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.SSM_D,
MODEL_TENSOR.SSM_OUT,
],
MODEL_ARCH.XVERSE: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_ROT_EMBD,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.COMMAND_R: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
@ -650,6 +668,10 @@ MODEL_TENSOR_SKIP: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
MODEL_ARCH.XVERSE: [
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
}
#