Skip to content

convert : fix null head_dim AutoConfig regression #14248

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 18, 2025
+16 −22
Merged

convert : fix null head_dim AutoConfig regression #14248

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 16 additions & 22 deletions convert_hf_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -556,11 +556,8 @@ def set_gguf_parameters(self):
logger.info(f"gguf: experts used count = {n_experts_used}")

if (head_dim := self.hparams.get("head_dim")) is not None:
# Workaround for incorrect AutoConfig value for DeepSeekV3 (is set correctly in DeepSeekV2Model class)
# https://github.com/huggingface/transformers/blob/19224c3642705c5b6988c9f5f4251f83323d05ae/src/transformers/models/deepseek_v3/configuration_deepseek_v3.py#L210
if self.hparams.get("model_type") != "deepseek_v3":
self.gguf_writer.add_key_length(head_dim)
self.gguf_writer.add_value_length(head_dim)
self.gguf_writer.add_key_length(head_dim)
self.gguf_writer.add_value_length(head_dim)

self.gguf_writer.add_file_type(self.ftype)
logger.info(f"gguf: file type = {self.ftype}")
Expand Down Expand Up @@ -1901,9 +1898,7 @@ def set_gguf_parameters(self):
hparams = self.hparams
self.gguf_writer.add_vocab_size(hparams["vocab_size"])

if "head_dim" in hparams:
rope_dim = hparams["head_dim"]
else:
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)

Expand Down Expand Up @@ -1985,7 +1980,8 @@ def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]:
if rope_scaling := self.find_hparam(["rope_scaling"], optional=True):
if rope_scaling.get("rope_type", '').lower() == "llama3":
base = self.hparams.get("rope_theta", 10000.0)
dim = self.hparams.get("head_dim", self.hparams["hidden_size"] // self.hparams["num_attention_heads"])
if (dim := self.hparams.get("head_dim")) is None:
dim = self.hparams["hidden_size"] // self.hparams["num_attention_heads"]
freqs = 1.0 / (base ** (torch.arange(0, dim, 2, dtype=torch.float32) / dim))

factor = rope_scaling.get("factor", 8.0)
Expand Down Expand Up @@ -2321,9 +2317,7 @@ def set_gguf_parameters(self):
hparams = self.hparams
self.gguf_writer.add_vocab_size(hparams["vocab_size"])

if "head_dim" in hparams:
rope_dim = hparams["head_dim"]
else:
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)

Expand Down Expand Up @@ -2363,7 +2357,8 @@ def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]:
if rope_scaling := self.find_hparam(["rope_scaling"], optional=True):
if rope_scaling.get("rope_type", '').lower() == "llama3":
base = self.hparams.get("rope_theta", 10000.0)
dim = self.hparams.get("head_dim", self.hparams["hidden_size"] // self.hparams["num_attention_heads"])
if (dim := self.hparams.get("head_dim")) is None:
dim = self.hparams["hidden_size"] // self.hparams["num_attention_heads"]
freqs = 1.0 / (base ** (torch.arange(0, dim, 2, dtype=torch.float32) / dim))

factor = rope_scaling.get("factor", 8.0)
Expand Down Expand Up @@ -3681,9 +3676,7 @@ def set_gguf_parameters(self):
hparams = self.hparams
self.gguf_writer.add_vocab_size(hparams["vocab_size"])

if "head_dim" in hparams:
rope_dim = hparams["head_dim"]
else:
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)

Expand Down Expand Up @@ -5098,9 +5091,7 @@ def set_vocab(self):
def set_gguf_parameters(self):
super().set_gguf_parameters()
hparams = self.hparams
if "head_dim" in hparams:
rope_dim = hparams["head_dim"]
else:
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)
Expand Down Expand Up @@ -5990,7 +5981,8 @@ def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]:
if rope_scaling := self.find_hparam(["rope_scaling"], optional=True):
if rope_scaling.get("rope_type", '').lower() == "llama3":
base = self.hparams.get("rope_theta", 10000.0)
dim = self.hparams.get("head_dim", self.hparams["hidden_size"] // self.hparams["num_attention_heads"])
if (dim := self.hparams.get("head_dim")) is None:
dim = self.hparams["hidden_size"] // self.hparams["num_attention_heads"]
freqs = 1.0 / (base ** (torch.arange(0, dim, 2, dtype=torch.float32) / dim))

factor = rope_scaling.get("factor", 8.0)
Expand Down Expand Up @@ -6102,7 +6094,8 @@ def set_vocab(self):
def set_gguf_parameters(self):
super().set_gguf_parameters()
hparams = self.hparams
rope_dim = hparams.get("head_dim") or hparams["hidden_size"] // hparams["num_attention_heads"]
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)
rope_scaling = self.hparams.get("rope_scaling") or {}
Expand Down Expand Up @@ -6134,7 +6127,8 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
n_head = self.hparams["num_attention_heads"]
n_kv_head = self.hparams.get("num_key_value_heads")
n_embd = self.hparams["hidden_size"]
head_dim = self.hparams.get("head_dim") or n_embd // n_head
if (head_dim := self.hparams.get("head_dim")) is None:
head_dim = n_embd // n_head

output_name = self.format_tensor_name(gguf.MODEL_TENSOR.OUTPUT)

Expand Down