Fix eos tokens to glm4 and adapts to glm3
This commit is contained in:
toyer
commit
e773174052
7 changed files with 476 additions and 10 deletions
|
|
@ -80,7 +80,7 @@ class Model:
|
|||
if not self.is_safetensors:
|
||||
self.part_names = Model.get_model_part_names(self.dir_model, "pytorch_model", ".bin")
|
||||
self.hparams = Model.load_hparams(self.dir_model)
|
||||
self.block_count = self.find_hparam(["n_layers", "num_hidden_layers", "n_layer"])
|
||||
self.block_count = self.find_hparam(["n_layers", "num_hidden_layers", "n_layer", "num_layers"])
|
||||
self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
|
||||
self.tensor_names = None
|
||||
if self.ftype == gguf.LlamaFileType.GUESSED:
|
||||
|
|
@ -483,6 +483,9 @@ class Model:
|
|||
if chkhsh == "7967bfa498ade6b757b064f31e964dddbb80f8f9a4d68d4ba7998fcf281c531a":
|
||||
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-code
|
||||
res = "jina-v2-code"
|
||||
if chkhsh == "b6e8e1518dc4305be2fe39c313ed643381c4da5db34a98f6a04c093f8afbe99b":
|
||||
# ref: https://huggingface.co/THUDM/glm-4-9b-chat
|
||||
res = "chatglm-bpe"
|
||||
|
||||
if res is None:
|
||||
logger.warning("\n")
|
||||
|
|
@ -2725,6 +2728,188 @@ class DeepseekV2Model(Model):
|
|||
raise ValueError(f"Unprocessed experts: {experts}")
|
||||
|
||||
|
||||
@Model.register("ChatGLMModel")
|
||||
class ChatGLMModel(Model):
|
||||
model_arch = gguf.MODEL_ARCH.CHATGLM
|
||||
|
||||
def set_vocab_chatglm3(self):
|
||||
dir_model = self.dir_model
|
||||
hparams = self.hparams
|
||||
tokens: list[bytearray] = []
|
||||
toktypes: list[int] = []
|
||||
scores: list[float] = []
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(dir_model, trust_remote_code=True)
|
||||
vocab_size = hparams.get("padded_vocab_size", len(tokenizer.get_vocab()))
|
||||
assert max(tokenizer.get_vocab().values()) < vocab_size
|
||||
role_special_tokens = ["<|system|>", "<|user|>", "<|assistant|>", "<|observation|>"]
|
||||
special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"] + role_special_tokens
|
||||
print(vocab_size)
|
||||
print(max(tokenizer.get_vocab().values()))
|
||||
for token_id in range(vocab_size):
|
||||
piece = tokenizer._convert_id_to_token(token_id)
|
||||
if token_id == 0:
|
||||
piece = "<unk>"
|
||||
elif token_id == 1:
|
||||
piece = "<bos>"
|
||||
elif token_id == 2:
|
||||
piece = "<eos>"
|
||||
|
||||
text = piece.encode("utf-8")
|
||||
score = 0.0
|
||||
# Referencing the tokenizer Python implementation(https://huggingface.co/THUDM/chatglm3-6b/blob/main/tokenization_chatglm.py),
|
||||
# it is only valid if it is less than tokenizer.tokenizer.sp_model.vocab_size()
|
||||
if len(piece) != 0 and token_id < tokenizer.tokenizer.sp_model.vocab_size():
|
||||
score = tokenizer.tokenizer.sp_model.get_score(token_id)
|
||||
|
||||
if len(piece) == 0:
|
||||
text = f"[PAD{token_id}]".encode("utf-8")
|
||||
|
||||
if token_id >= tokenizer.tokenizer.sp_model.vocab_size():
|
||||
if piece in special_tokens:
|
||||
# show special tokens in prompt
|
||||
toktype = SentencePieceTokenTypes.USER_DEFINED
|
||||
else:
|
||||
toktype = SentencePieceTokenTypes.UNKNOWN
|
||||
tokens.append(text)
|
||||
scores.append(score)
|
||||
toktypes.append(toktype)
|
||||
continue
|
||||
|
||||
toktype = SentencePieceTokenTypes.NORMAL
|
||||
if tokenizer.tokenizer.sp_model.is_unknown(token_id):
|
||||
toktype = SentencePieceTokenTypes.UNKNOWN
|
||||
elif tokenizer.tokenizer.sp_model.is_control(token_id):
|
||||
toktype = SentencePieceTokenTypes.CONTROL
|
||||
elif tokenizer.tokenizer.sp_model.is_unused(token_id):
|
||||
toktype = SentencePieceTokenTypes.UNUSED
|
||||
elif tokenizer.tokenizer.sp_model.is_byte(token_id):
|
||||
toktype = SentencePieceTokenTypes.BYTE
|
||||
|
||||
tokens.append(text)
|
||||
scores.append(score)
|
||||
toktypes.append(toktype)
|
||||
|
||||
self.gguf_writer.add_tokenizer_model("llama")
|
||||
self.gguf_writer.add_token_list(tokens)
|
||||
self.gguf_writer.add_token_scores(scores)
|
||||
self.gguf_writer.add_token_types(toktypes)
|
||||
|
||||
special_vocab = gguf.SpecialVocab(self.dir_model, n_vocab=len(tokens))
|
||||
special_vocab.add_to_gguf(self.gguf_writer)
|
||||
|
||||
@staticmethod
|
||||
def token_bytes_to_string(b):
|
||||
from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
|
||||
byte_encoder = bytes_to_unicode()
|
||||
return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')])
|
||||
|
||||
@staticmethod
|
||||
def bpe(mergeable_ranks: dict[bytes, int], token: bytes, max_rank: int | None = None) -> list[bytes]:
|
||||
parts = [bytes([b]) for b in token]
|
||||
while True:
|
||||
min_idx = None
|
||||
min_rank = None
|
||||
for i, pair in enumerate(zip(parts[:-1], parts[1:])):
|
||||
rank = mergeable_ranks.get(pair[0] + pair[1])
|
||||
if rank is not None and (min_rank is None or rank < min_rank):
|
||||
min_idx = i
|
||||
min_rank = rank
|
||||
if min_rank is None or (max_rank is not None and min_rank >= max_rank):
|
||||
break
|
||||
assert min_idx is not None
|
||||
parts = parts[:min_idx] + [parts[min_idx] + parts[min_idx + 1]] + parts[min_idx + 2:]
|
||||
return parts
|
||||
|
||||
def set_vocab(self):
|
||||
if "THUDM/chatglm3-6b" in self.hparams.get("_name_or_path", ""):
|
||||
self.set_vocab_chatglm3()
|
||||
return
|
||||
|
||||
dir_model = self.dir_model
|
||||
hparams = self.hparams
|
||||
tokens: list[str] = []
|
||||
toktypes: list[int] = []
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(dir_model, trust_remote_code=True)
|
||||
vocab_size = hparams["padded_vocab_size"]
|
||||
assert max(tokenizer.get_vocab().values()) < vocab_size
|
||||
|
||||
tokpre = self.get_vocab_base_pre(tokenizer)
|
||||
|
||||
merges = []
|
||||
vocab = {}
|
||||
mergeable_ranks = tokenizer.mergeable_ranks
|
||||
for token, rank in mergeable_ranks.items():
|
||||
vocab[ChatGLMModel.token_bytes_to_string(token)] = rank
|
||||
if len(token) == 1:
|
||||
continue
|
||||
merged = ChatGLMModel.bpe(mergeable_ranks, token, max_rank=rank)
|
||||
assert len(merged) >= 2 and len(merged) <= 7
|
||||
merges.append(' '.join(map(ChatGLMModel.token_bytes_to_string, merged)))
|
||||
|
||||
# for this kind of tokenizer, added_vocab is not a subset of vocab, so they need to be combined
|
||||
added_vocab = tokenizer.get_added_vocab()
|
||||
reverse_vocab = {id_ : encoded_tok for encoded_tok, id_ in {**vocab, **added_vocab}.items()}
|
||||
|
||||
for i in range(vocab_size):
|
||||
if i not in reverse_vocab:
|
||||
tokens.append(f"[PAD{i}]")
|
||||
toktypes.append(gguf.TokenType.USER_DEFINED)
|
||||
elif reverse_vocab[i] in added_vocab:
|
||||
tokens.append(reverse_vocab[i])
|
||||
if tokenizer.added_tokens_decoder[i].special:
|
||||
toktypes.append(gguf.TokenType.CONTROL)
|
||||
else:
|
||||
toktypes.append(gguf.TokenType.USER_DEFINED)
|
||||
else:
|
||||
tokens.append(reverse_vocab[i])
|
||||
toktypes.append(gguf.TokenType.NORMAL)
|
||||
|
||||
self.gguf_writer.add_tokenizer_model("gpt2")
|
||||
self.gguf_writer.add_tokenizer_pre(tokpre)
|
||||
self.gguf_writer.add_token_list(tokens)
|
||||
self.gguf_writer.add_token_types(toktypes)
|
||||
|
||||
special_vocab = gguf.SpecialVocab(dir_model, load_merges=False)
|
||||
special_vocab.chat_template = "ChatGLM4"
|
||||
special_vocab.merges = merges
|
||||
# only add special tokens when they were not already loaded from config.json
|
||||
# if len(special_vocab.special_token_ids) == 0:
|
||||
special_vocab._set_special_token("bos", tokenizer.get_added_vocab()["<|endoftext|>"])
|
||||
special_vocab._set_special_token("eos", tokenizer.get_added_vocab()["<|endoftext|>"])
|
||||
# this one is usually not in config.json anyway
|
||||
special_vocab._set_special_token("unk", tokenizer.get_added_vocab()["<|endoftext|>"])
|
||||
special_vocab.add_to_gguf(self.gguf_writer)
|
||||
|
||||
def set_gguf_parameters(self):
|
||||
self.gguf_writer.add_name(self.dir_model.name)
|
||||
n_embed = self.hparams.get("hidden_size", self.hparams.get("n_embed"))
|
||||
n_head = self.hparams.get("n_head", self.hparams.get("num_attention_heads"))
|
||||
n_head_kv = self.hparams.get("multi_query_group_num", n_head)
|
||||
self.gguf_writer.add_context_length(self.hparams.get("seq_length", n_embed))
|
||||
self.gguf_writer.add_embedding_length(n_embed)
|
||||
self.gguf_writer.add_feed_forward_length(self.hparams.get("ffn_hidden_size", 4 * n_embed))
|
||||
self.gguf_writer.add_block_count(self.hparams["num_layers"])
|
||||
self.gguf_writer.add_head_count(n_head)
|
||||
self.gguf_writer.add_head_count_kv(n_head_kv)
|
||||
self.gguf_writer.add_layer_norm_rms_eps(self.hparams["layernorm_epsilon"])
|
||||
self.gguf_writer.add_file_type(self.ftype)
|
||||
self.gguf_writer.add_rope_dimension_count(64)
|
||||
self.gguf_writer.add_add_bos_token(False)
|
||||
|
||||
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
|
||||
del bid # unused
|
||||
|
||||
if name.endswith(".rotary_pos_emb.inv_freq"):
|
||||
return []
|
||||
|
||||
name = name.removeprefix("transformer.")
|
||||
return [(self.map_tensor_name(name), data_torch)]
|
||||
|
||||
|
||||
###### CONVERSION LOGIC ######
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue