ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : add PLM GGUF Conversion & Inference Support (#12457)

Browse source 
* add edgellm model arch[conversation feature doesn't work]

* remove output.weight layer for edgellm arch

* [Model] update the name of the model

* update the name of model arch in convert gguf

* [Model] Refarctor the model arch into llama-model

* [Bug] Fix the bug in create attn kv

* [Code] Fix editorconfig erros

* [Code] Remove Trailing whitespace

* [Code] Remove Trailing whitespace

* [Code] Change the order of model arch in list

* [Code] Fix flake8 Lint errors

* Remove trailing white space

* [Code] Remove  call in model arch
This commit is contained in:
Si1w 2025-03-27 10:49:15 +00:00 • committed by GitHub
parent 953c2a62cf
commit f125b8dccf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 274 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

23
convert_hf_to_gguf.py
View file

@ -4419,6 +4419,29 @@ class DeepseekV2Model(Model):
raise ValueError(f"Unprocessed experts: {experts}")
@Model.register("PLMForCausalLM")
class PLMModel(Model):
model_arch = gguf.MODEL_ARCH.PLM
def set_vocab(self):
self._set_vocab_gpt2()
def set_gguf_parameters(self):
super().set_gguf_parameters()
hparams = self.hparams
self.gguf_writer.add_vocab_size(hparams["vocab_size"])
self.gguf_writer.add_kv_lora_rank(hparams["kv_lora_rank"])
self.gguf_writer.add_key_length(hparams["qk_nope_head_dim"] + hparams["qk_rope_head_dim"])
self.gguf_writer.add_value_length(hparams["v_head_dim"])
self.gguf_writer.add_rope_dimension_count(hparams["qk_rope_head_dim"])
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
return [(self.map_tensor_name(name), data_torch)]
def prepare_tensors(self):
super().prepare_tensors()
@Model.register("T5WithLMHeadModel")
@Model.register("T5ForConditionalGeneration")
@Model.register("MT5ForConditionalGeneration")