Skip to content

added qwen3.5 support #438

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

Open
TheJoshCode wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

added qwen3.5 support #438

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
4 changes: 2 additions & 2 deletions loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
from .dequant import is_quantized, dequantize_tensor

IMG_ARCH_LIST = {"flux", "sd1", "sdxl", "sd3", "aura", "hidream", "cosmos", "ltxv", "hyvid", "wan", "lumina2", "qwen_image"}
TXT_ARCH_LIST = {"t5", "t5encoder", "llama", "qwen2vl", "qwen3", "qwen3vl", "gemma3"}
TXT_ARCH_LIST = {"t5", "t5encoder", "llama", "qwen2vl", "qwen3", "qwen35", "qwen3vl", "gemma3"}
VIS_TYPE_LIST = {"clip-vision", "mmproj"}

def get_orig_shape(reader, tensor_name):
Expand Down Expand Up @@ -479,7 +479,7 @@ def gguf_clip_loader(path):
logging.warning(f"Dequantizing {temb_key} to prevent runtime OOM.")
sd[temb_key] = dequantize_tensor(sd[temb_key], dtype=torch.float16)
sd = sd_map_replace(sd, T5_SD_MAP)
elif arch in {"llama", "qwen2vl", "qwen3", "qwen3vl", "gemma3"}:
elif arch in {"llama", "qwen2vl", "qwen3", "qwen3vl", "qwen35", "gemma3"}:
# TODO: pass model_options["vocab_size"] to loader somehow
temb_key = "token_embd.weight"
if temb_key in sd and sd[temb_key].shape[0] >= (64 * 1024):
Expand Down