root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 11:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

add placeholder of starcoder in gguf / llama.cpp

Browse Source
This commit is contained in:
Meng Zhang 2023-09-15 10:38:46 +08:00
parent 98311c4277
commit 0c5d4d87b0
2 changed files with 27 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
gguf-py/gguf/gguf.py
View File

@ -77,13 +77,14 @@ KEY_TOKENIZER_RWKV = "tokenizer.rwkv.world"
class MODEL_ARCH(IntEnum):
LLAMA : int = auto()
FALCON : int = auto()
BAICHUAN:int = auto()
GPT2 : int = auto()
GPTJ : int = auto()
GPTNEOX: int = auto()
MPT : int = auto()
LLAMA : int = auto()
FALCON : int = auto()
BAICHUAN : int = auto()
GPT2 : int = auto()
GPTJ : int = auto()
GPTNEOX : int = auto()
MPT : int = auto()
STARCODER : int = auto()
class MODEL_TENSOR(IntEnum):
@ -107,13 +108,14 @@ class MODEL_TENSOR(IntEnum):
MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.LLAMA: "llama",
MODEL_ARCH.FALCON: "falcon",
MODEL_ARCH.BAICHUAN:"baichuan",
MODEL_ARCH.GPT2: "gpt2",
MODEL_ARCH.GPTJ: "gptj",
MODEL_ARCH.GPTNEOX: "gptneox",
MODEL_ARCH.MPT: "mpt",
MODEL_ARCH.LLAMA: "llama",
MODEL_ARCH.FALCON: "falcon",
MODEL_ARCH.BAICHUAN: "baichuan",
MODEL_ARCH.GPT2: "gpt2",
MODEL_ARCH.GPTJ: "gptj",
MODEL_ARCH.GPTNEOX: "gptneox",
MODEL_ARCH.MPT: "mpt",
MODEL_ARCH.STARCODER: "starcoder",
}
MODEL_TENSOR_NAMES: dict[MODEL_ARCH, dict[MODEL_TENSOR, str]] = {
@ -171,6 +173,8 @@ MODEL_TENSOR_NAMES: dict[MODEL_ARCH, dict[MODEL_TENSOR, str]] = {
MODEL_TENSOR.FFN_DOWN: "blk.{bid}.ffn_down",
MODEL_TENSOR.FFN_UP: "blk.{bid}.ffn_up",
},
MODEL_ARCH.STARCODER: {
},
MODEL_ARCH.GPT2: {
# TODO
},

16
llama.cpp
View File

@ -160,17 +160,19 @@ enum llm_arch {
LLM_ARCH_GPTJ,
LLM_ARCH_GPTNEOX,
LLM_ARCH_MPT,
LLM_ARCH_STARCODER,
LLM_ARCH_UNKNOWN,
};
static std::map<llm_arch, std::string> LLM_ARCH_NAMES = {
{ LLM_ARCH_LLAMA, "llama" },
{ LLM_ARCH_FALCON, "falcon" },
{ LLM_ARCH_GPT2, "gpt2" },
{ LLM_ARCH_GPTJ, "gptj" },
{ LLM_ARCH_GPTNEOX, "gptneox" },
{ LLM_ARCH_MPT, "mpt" },
{ LLM_ARCH_BAICHUAN,"baichuan" },
{ LLM_ARCH_LLAMA, "llama" },
{ LLM_ARCH_FALCON, "falcon" },
{ LLM_ARCH_GPT2, "gpt2" },
{ LLM_ARCH_GPTJ, "gptj" },
{ LLM_ARCH_GPTNEOX, "gptneox" },
{ LLM_ARCH_MPT, "mpt" },
{ LLM_ARCH_BAICHUAN, "baichuan" },
{ LLM_ARCH_STARCODER, "starcoder" },
};
enum llm_kv {