Merge branch 'master' into compilade/mamba2
This commit is contained in:
commit
038d958333
132 changed files with 6559 additions and 5146 deletions
|
@ -153,6 +153,8 @@ class Keys:
|
|||
MERGES = "tokenizer.ggml.merges"
|
||||
BOS_ID = "tokenizer.ggml.bos_token_id"
|
||||
EOS_ID = "tokenizer.ggml.eos_token_id"
|
||||
EOT_ID = "tokenizer.ggml.eot_token_id"
|
||||
EOM_ID = "tokenizer.ggml.eom_token_id"
|
||||
UNK_ID = "tokenizer.ggml.unknown_token_id"
|
||||
SEP_ID = "tokenizer.ggml.seperator_token_id"
|
||||
PAD_ID = "tokenizer.ggml.padding_token_id"
|
||||
|
@ -169,11 +171,16 @@ class Keys:
|
|||
CHAT_TEMPLATE_N = "tokenizer.chat_template.{name}"
|
||||
CHAT_TEMPLATES = "tokenizer.chat_templates"
|
||||
# FIM/Infill special tokens constants
|
||||
FIM_PRE_ID = "tokenizer.ggml.fim_pre_token_id"
|
||||
FIM_SUF_ID = "tokenizer.ggml.fim_suf_token_id"
|
||||
FIM_MID_ID = "tokenizer.ggml.fim_mid_token_id"
|
||||
FIM_PAD_ID = "tokenizer.ggml.fim_pad_token_id"
|
||||
FIM_REP_ID = "tokenizer.ggml.fim_rep_token_id"
|
||||
FIM_SEP_ID = "tokenizer.ggml.fim_sep_token_id"
|
||||
# deprecated:
|
||||
PREFIX_ID = "tokenizer.ggml.prefix_token_id"
|
||||
SUFFIX_ID = "tokenizer.ggml.suffix_token_id"
|
||||
MIDDLE_ID = "tokenizer.ggml.middle_token_id"
|
||||
EOT_ID = "tokenizer.ggml.eot_token_id"
|
||||
EOM_ID = "tokenizer.ggml.eom_token_id"
|
||||
|
||||
class Adapter:
|
||||
TYPE = "adapter.type"
|
||||
|
@ -1598,6 +1605,8 @@ KEY_TOKENIZER_SCORES = Keys.Tokenizer.SCORES
|
|||
KEY_TOKENIZER_MERGES = Keys.Tokenizer.MERGES
|
||||
KEY_TOKENIZER_BOS_ID = Keys.Tokenizer.BOS_ID
|
||||
KEY_TOKENIZER_EOS_ID = Keys.Tokenizer.EOS_ID
|
||||
KEY_TOKENIZER_EOT_ID = Keys.Tokenizer.EOT_ID
|
||||
KEY_TOKENIZER_EOM_ID = Keys.Tokenizer.EOM_ID
|
||||
KEY_TOKENIZER_UNK_ID = Keys.Tokenizer.UNK_ID
|
||||
KEY_TOKENIZER_SEP_ID = Keys.Tokenizer.SEP_ID
|
||||
KEY_TOKENIZER_PAD_ID = Keys.Tokenizer.PAD_ID
|
||||
|
@ -1605,8 +1614,15 @@ KEY_TOKENIZER_CLS_ID = Keys.Tokenizer.CLS_ID
|
|||
KEY_TOKENIZER_MASK_ID = Keys.Tokenizer.MASK_ID
|
||||
KEY_TOKENIZER_HF_JSON = Keys.Tokenizer.HF_JSON
|
||||
KEY_TOKENIZER_RWKV = Keys.Tokenizer.RWKV
|
||||
KEY_TOKENIZER_PRIFIX_ID = Keys.Tokenizer.PREFIX_ID
|
||||
|
||||
KEY_TOKENIZER_FIM_PRE_ID = Keys.Tokenizer.FIM_PRE_ID
|
||||
KEY_TOKENIZER_FIM_SUF_ID = Keys.Tokenizer.FIM_SUF_ID
|
||||
KEY_TOKENIZER_FIM_MID_ID = Keys.Tokenizer.FIM_MID_ID
|
||||
KEY_TOKENIZER_FIM_PAD_ID = Keys.Tokenizer.FIM_PAD_ID
|
||||
KEY_TOKENIZER_FIM_REP_ID = Keys.Tokenizer.FIM_REP_ID
|
||||
KEY_TOKENIZER_FIM_SEP_ID = Keys.Tokenizer.FIM_SEP_ID
|
||||
|
||||
# deprecated
|
||||
KEY_TOKENIZER_PREFIX_ID = Keys.Tokenizer.PREFIX_ID
|
||||
KEY_TOKENIZER_SUFFIX_ID = Keys.Tokenizer.SUFFIX_ID
|
||||
KEY_TOKENIZER_MIDDLE_ID = Keys.Tokenizer.MIDDLE_ID
|
||||
KEY_TOKENIZER_EOT_ID = Keys.Tokenizer.EOT_ID
|
||||
KEY_TOKENIZER_EOM_ID = Keys.Tokenizer.EOM_ID
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue