Merge branch 'master' into compilade/bitnet-ternary
This commit is contained in:
Francis Couture-Harpin
commit
79a278e922
340 changed files with 43840 additions and 162220 deletions
|
|
@ -19,18 +19,60 @@ GGML_QUANT_VERSION = 2 # GGML_QNT_VERSION from ggml.h
|
|||
|
||||
class Keys:
|
||||
class General:
|
||||
ARCHITECTURE = "general.architecture"
|
||||
QUANTIZATION_VERSION = "general.quantization_version"
|
||||
ALIGNMENT = "general.alignment"
|
||||
NAME = "general.name"
|
||||
AUTHOR = "general.author"
|
||||
VERSION = "general.version"
|
||||
URL = "general.url"
|
||||
DESCRIPTION = "general.description"
|
||||
LICENSE = "general.license"
|
||||
SOURCE_URL = "general.source.url"
|
||||
SOURCE_HF_REPO = "general.source.huggingface.repository"
|
||||
FILE_TYPE = "general.file_type"
|
||||
TYPE = "general.type"
|
||||
ARCHITECTURE = "general.architecture"
|
||||
QUANTIZATION_VERSION = "general.quantization_version"
|
||||
ALIGNMENT = "general.alignment"
|
||||
FILE_TYPE = "general.file_type"
|
||||
|
||||
# Authorship Metadata
|
||||
NAME = "general.name"
|
||||
AUTHOR = "general.author"
|
||||
VERSION = "general.version"
|
||||
ORGANIZATION = "general.organization"
|
||||
|
||||
FINETUNE = "general.finetune"
|
||||
BASENAME = "general.basename"
|
||||
|
||||
DESCRIPTION = "general.description"
|
||||
QUANTIZED_BY = "general.quantized_by"
|
||||
|
||||
SIZE_LABEL = "general.size_label"
|
||||
|
||||
# Licensing details
|
||||
LICENSE = "general.license"
|
||||
LICENSE_NAME = "general.license.name"
|
||||
LICENSE_LINK = "general.license.link"
|
||||
|
||||
# Typically represents the converted GGUF repo (Unless native)
|
||||
URL = "general.url" # Model Website/Paper
|
||||
DOI = "general.doi"
|
||||
UUID = "general.uuid"
|
||||
REPO_URL = "general.repo_url" # Model Source Repository (git/svn/etc...)
|
||||
|
||||
# Model Source during conversion
|
||||
SOURCE_URL = "general.source.url" # Model Website/Paper
|
||||
SOURCE_DOI = "general.source.doi"
|
||||
SOURCE_UUID = "general.source.uuid"
|
||||
SOURCE_REPO_URL = "general.source.repo_url" # Model Source Repository (git/svn/etc...)
|
||||
|
||||
# Base Model Source. There can be more than one source if it's a merged
|
||||
# model like with 'Mistral-7B-Merge-14-v0.1'. This will assist in
|
||||
# tracing linage of models as it is finetuned or merged over time.
|
||||
BASE_MODEL_COUNT = "general.base_model.count"
|
||||
BASE_MODEL_NAME = "general.base_model.{id}.name"
|
||||
BASE_MODEL_AUTHOR = "general.base_model.{id}.author"
|
||||
BASE_MODEL_VERSION = "general.base_model.{id}.version"
|
||||
BASE_MODEL_ORGANIZATION = "general.base_model.{id}.organization"
|
||||
BASE_MODEL_URL = "general.base_model.{id}.url" # Model Website/Paper
|
||||
BASE_MODEL_DOI = "general.base_model.{id}.doi"
|
||||
BASE_MODEL_UUID = "general.base_model.{id}.uuid"
|
||||
BASE_MODEL_REPO_URL = "general.base_model.{id}.repo_url" # Model Source Repository (git/svn/etc...)
|
||||
|
||||
# Array based KV stores
|
||||
TAGS = "general.tags"
|
||||
LANGUAGES = "general.languages"
|
||||
DATASETS = "general.datasets"
|
||||
|
||||
class LLM:
|
||||
VOCAB_SIZE = "{arch}.vocab_size"
|
||||
|
|
@ -50,6 +92,8 @@ class Keys:
|
|||
POOLING_TYPE = "{arch}.pooling_type"
|
||||
LOGIT_SCALE = "{arch}.logit_scale"
|
||||
DECODER_START_TOKEN_ID = "{arch}.decoder_start_token_id"
|
||||
ATTN_LOGIT_SOFTCAPPING = "{arch}.attn_logit_softcapping"
|
||||
FINAL_LOGIT_SOFTCAPPING = "{arch}.final_logit_softcapping"
|
||||
|
||||
class Attention:
|
||||
HEAD_COUNT = "{arch}.attention.head_count"
|
||||
|
|
@ -64,6 +108,7 @@ class Keys:
|
|||
Q_LORA_RANK = "{arch}.attention.q_lora_rank"
|
||||
KV_LORA_RANK = "{arch}.attention.kv_lora_rank"
|
||||
REL_BUCKETS_COUNT = "{arch}.attention.relative_buckets_count"
|
||||
SLIDING_WINDOW = "{arch}.attention.sliding_window"
|
||||
|
||||
class Rope:
|
||||
DIMENSION_COUNT = "{arch}.rope.dimension_count"
|
||||
|
|
@ -117,12 +162,20 @@ class Keys:
|
|||
MIDDLE_ID = "tokenizer.ggml.middle_token_id"
|
||||
EOT_ID = "tokenizer.ggml.eot_token_id"
|
||||
|
||||
class Adapter:
|
||||
TYPE = "adapter.type"
|
||||
LORA_ALPHA = "adapter.lora.alpha"
|
||||
|
||||
#
|
||||
# recommended mapping of model tensor names for storage in gguf
|
||||
#
|
||||
|
||||
|
||||
class GGUFType:
|
||||
MODEL = "model"
|
||||
ADAPTER = "adapter"
|
||||
|
||||
|
||||
class MODEL_ARCH(IntEnum):
|
||||
LLAMA = auto()
|
||||
FALCON = auto()
|
||||
|
|
@ -150,16 +203,20 @@ class MODEL_ARCH(IntEnum):
|
|||
INTERNLM2 = auto()
|
||||
MINICPM = auto()
|
||||
GEMMA = auto()
|
||||
GEMMA2 = auto()
|
||||
STARCODER2 = auto()
|
||||
MAMBA = auto()
|
||||
XVERSE = auto()
|
||||
COMMAND_R = auto()
|
||||
DBRX = auto()
|
||||
OLMO = auto()
|
||||
OPENELM = auto()
|
||||
ARCTIC = auto()
|
||||
DEEPSEEK2 = auto()
|
||||
CHATGLM = auto()
|
||||
BITNET = auto()
|
||||
T5 = auto()
|
||||
JAIS = auto()
|
||||
|
||||
|
||||
class MODEL_TENSOR(IntEnum):
|
||||
|
|
@ -180,10 +237,13 @@ class MODEL_TENSOR(IntEnum):
|
|||
ATTN_NORM = auto()
|
||||
ATTN_NORM_2 = auto()
|
||||
ATTN_OUT_NORM = auto()
|
||||
ATTN_POST_NORM = auto()
|
||||
ATTN_ROT_EMBD = auto()
|
||||
FFN_GATE_INP = auto()
|
||||
FFN_GATE_INP_SHEXP = auto()
|
||||
FFN_NORM = auto()
|
||||
FFN_PRE_NORM = auto()
|
||||
FFN_POST_NORM = auto()
|
||||
FFN_GATE = auto()
|
||||
FFN_DOWN = auto()
|
||||
FFN_UP = auto()
|
||||
|
|
@ -270,16 +330,20 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
|
|||
MODEL_ARCH.INTERNLM2: "internlm2",
|
||||
MODEL_ARCH.MINICPM: "minicpm",
|
||||
MODEL_ARCH.GEMMA: "gemma",
|
||||
MODEL_ARCH.GEMMA2: "gemma2",
|
||||
MODEL_ARCH.STARCODER2: "starcoder2",
|
||||
MODEL_ARCH.MAMBA: "mamba",
|
||||
MODEL_ARCH.XVERSE: "xverse",
|
||||
MODEL_ARCH.COMMAND_R: "command-r",
|
||||
MODEL_ARCH.DBRX: "dbrx",
|
||||
MODEL_ARCH.OLMO: "olmo",
|
||||
MODEL_ARCH.OPENELM: "openelm",
|
||||
MODEL_ARCH.ARCTIC: "arctic",
|
||||
MODEL_ARCH.DEEPSEEK2: "deepseek2",
|
||||
MODEL_ARCH.CHATGLM: "chatglm",
|
||||
MODEL_ARCH.BITNET: "bitnet",
|
||||
MODEL_ARCH.T5: "t5",
|
||||
MODEL_ARCH.JAIS: "jais",
|
||||
}
|
||||
|
||||
TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
|
||||
|
|
@ -303,9 +367,12 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
|
|||
MODEL_TENSOR.ATTN_Q_NORM: "blk.{bid}.attn_q_norm",
|
||||
MODEL_TENSOR.ATTN_K_NORM: "blk.{bid}.attn_k_norm",
|
||||
MODEL_TENSOR.ATTN_OUT_NORM: "blk.{bid}.attn_output_norm",
|
||||
MODEL_TENSOR.ATTN_POST_NORM: "blk.{bid}.post_attention_norm",
|
||||
MODEL_TENSOR.FFN_GATE_INP: "blk.{bid}.ffn_gate_inp",
|
||||
MODEL_TENSOR.FFN_GATE_INP_SHEXP: "blk.{bid}.ffn_gate_inp_shexp",
|
||||
MODEL_TENSOR.FFN_NORM: "blk.{bid}.ffn_norm",
|
||||
MODEL_TENSOR.FFN_PRE_NORM: "blk.{bid}.ffn_norm",
|
||||
MODEL_TENSOR.FFN_POST_NORM: "blk.{bid}.post_ffw_norm",
|
||||
MODEL_TENSOR.FFN_GATE: "blk.{bid}.ffn_gate",
|
||||
MODEL_TENSOR.FFN_DOWN: "blk.{bid}.ffn_down",
|
||||
MODEL_TENSOR.FFN_UP: "blk.{bid}.ffn_up",
|
||||
|
|
@ -751,6 +818,21 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
|||
MODEL_TENSOR.FFN_UP,
|
||||
MODEL_TENSOR.FFN_NORM,
|
||||
],
|
||||
MODEL_ARCH.GEMMA2: [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
MODEL_TENSOR.OUTPUT_NORM,
|
||||
MODEL_TENSOR.ATTN_Q,
|
||||
MODEL_TENSOR.ATTN_K,
|
||||
MODEL_TENSOR.ATTN_V,
|
||||
MODEL_TENSOR.ATTN_OUT,
|
||||
MODEL_TENSOR.FFN_GATE,
|
||||
MODEL_TENSOR.FFN_DOWN,
|
||||
MODEL_TENSOR.FFN_UP,
|
||||
MODEL_TENSOR.ATTN_NORM,
|
||||
MODEL_TENSOR.ATTN_POST_NORM,
|
||||
MODEL_TENSOR.FFN_PRE_NORM,
|
||||
MODEL_TENSOR.FFN_POST_NORM,
|
||||
],
|
||||
MODEL_ARCH.STARCODER2: [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
MODEL_TENSOR.OUTPUT_NORM,
|
||||
|
|
@ -833,6 +915,19 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
|||
MODEL_TENSOR.FFN_DOWN,
|
||||
MODEL_TENSOR.FFN_UP,
|
||||
],
|
||||
MODEL_ARCH.OPENELM: [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
MODEL_TENSOR.OUTPUT_NORM,
|
||||
MODEL_TENSOR.ATTN_NORM,
|
||||
MODEL_TENSOR.ATTN_QKV,
|
||||
MODEL_TENSOR.ATTN_Q_NORM,
|
||||
MODEL_TENSOR.ATTN_K_NORM,
|
||||
MODEL_TENSOR.ATTN_OUT,
|
||||
MODEL_TENSOR.FFN_NORM,
|
||||
MODEL_TENSOR.FFN_GATE,
|
||||
MODEL_TENSOR.FFN_DOWN,
|
||||
MODEL_TENSOR.FFN_UP,
|
||||
],
|
||||
MODEL_ARCH.ARCTIC: [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
MODEL_TENSOR.OUTPUT_NORM,
|
||||
|
|
@ -881,6 +976,18 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
|||
MODEL_TENSOR.FFN_DOWN_SHEXP,
|
||||
MODEL_TENSOR.FFN_UP_SHEXP,
|
||||
],
|
||||
MODEL_ARCH.CHATGLM : [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
MODEL_TENSOR.ROPE_FREQS,
|
||||
MODEL_TENSOR.OUTPUT_NORM,
|
||||
MODEL_TENSOR.OUTPUT,
|
||||
MODEL_TENSOR.ATTN_NORM,
|
||||
MODEL_TENSOR.ATTN_QKV,
|
||||
MODEL_TENSOR.ATTN_OUT,
|
||||
MODEL_TENSOR.FFN_NORM,
|
||||
MODEL_TENSOR.FFN_DOWN,
|
||||
MODEL_TENSOR.FFN_UP,
|
||||
],
|
||||
MODEL_ARCH.BITNET: [
|
||||
MODEL_TENSOR.ATTN_Q,
|
||||
MODEL_TENSOR.ATTN_K,
|
||||
|
|
@ -928,6 +1035,18 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
|||
MODEL_TENSOR.ENC_FFN_UP,
|
||||
MODEL_TENSOR.ENC_OUTPUT_NORM,
|
||||
],
|
||||
MODEL_ARCH.JAIS: [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
MODEL_TENSOR.OUTPUT_NORM,
|
||||
MODEL_TENSOR.OUTPUT,
|
||||
MODEL_TENSOR.ATTN_NORM,
|
||||
MODEL_TENSOR.ATTN_QKV,
|
||||
MODEL_TENSOR.ATTN_OUT,
|
||||
MODEL_TENSOR.FFN_NORM,
|
||||
MODEL_TENSOR.FFN_DOWN,
|
||||
MODEL_TENSOR.FFN_GATE,
|
||||
MODEL_TENSOR.FFN_UP,
|
||||
],
|
||||
# TODO
|
||||
}
|
||||
|
||||
|
|
@ -965,6 +1084,9 @@ MODEL_TENSOR_SKIP: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
|||
MODEL_TENSOR.ROPE_FREQS,
|
||||
MODEL_TENSOR.ATTN_ROT_EMBD,
|
||||
],
|
||||
MODEL_ARCH.CHATGLM: [
|
||||
MODEL_TENSOR.ROPE_FREQS,
|
||||
],
|
||||
}
|
||||
|
||||
#
|
||||
|
|
@ -1158,7 +1280,6 @@ KEY_GENERAL_URL = Keys.General.URL
|
|||
KEY_GENERAL_DESCRIPTION = Keys.General.DESCRIPTION
|
||||
KEY_GENERAL_LICENSE = Keys.General.LICENSE
|
||||
KEY_GENERAL_SOURCE_URL = Keys.General.SOURCE_URL
|
||||
KEY_GENERAL_SOURCE_HF_REPO = Keys.General.SOURCE_HF_REPO
|
||||
KEY_GENERAL_FILE_TYPE = Keys.General.FILE_TYPE
|
||||
|
||||
# LLM
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue