wehub-resource-sync
09a3d3ab17
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Python check requirements.txt / check-requirements (push) Waiting to run
Python Type-Check / python type-check (push) Waiting to run
Update Operations Documentation / update-ops-docs (push) Waiting to run
Copilot Setup Steps / copilot-setup-steps (push) Failing after 2s
47 lines
1.7 KiB
Python
47 lines
1.7 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
from typing import Iterable, TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from torch import Tensor
|
|
|
|
from .base import ModelBase, TextModel, gguf, logger
|
|
|
|
|
|
@ModelBase.register("PanguEmbeddedForCausalLM")
|
|
class PanguEmbeddedModel(TextModel):
|
|
model_arch = gguf.MODEL_ARCH.PANGU_EMBED
|
|
|
|
def set_vocab(self):
|
|
self._set_vocab_sentencepiece()
|
|
|
|
tokenizer_config_file = self.dir_model / 'tokenizer_config.json'
|
|
if tokenizer_config_file.is_file():
|
|
with open(tokenizer_config_file, "r", encoding="utf-8") as f:
|
|
tokenizer_config_json = json.load(f)
|
|
if "add_prefix_space" in tokenizer_config_json:
|
|
self.gguf_writer.add_add_space_prefix(tokenizer_config_json["add_prefix_space"])
|
|
|
|
def set_gguf_parameters(self):
|
|
super().set_gguf_parameters()
|
|
hparams = self.hparams
|
|
self.gguf_writer.add_vocab_size(hparams["vocab_size"])
|
|
|
|
# PanguEmbedded's hparam loaded from config.json without head_dim
|
|
if (rope_dim := hparams.get("head_dim")) is None:
|
|
rope_dim = hparams["hidden_size"] // hparams["num_attention_heads"]
|
|
self.gguf_writer.add_rope_dimension_count(rope_dim)
|
|
|
|
if hparams.get("head_dim") is None:
|
|
self.gguf_writer.add_key_length(rope_dim)
|
|
self.gguf_writer.add_value_length(rope_dim)
|
|
|
|
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
|
|
if name == "lm_head.weight":
|
|
if self.hparams.get("tie_word_embeddings", False):
|
|
logger.info("Skipping tied output layer 'lm_head.weight'")
|
|
return
|
|
yield from super().modify_tensors(data_torch, name, bid)
|