ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support llava-next(video)

Browse Source 
Former-commit-id: 27e94593ac467e56e3a7f5c64f4ff6cee81f4b47
This commit is contained in:
BUAADreamer
2024-09-10 12:31:53 +08:00
parent dfff411e1a
commit 484128b641
11 changed files with 394 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llamafactory/model/model_utils/visual.py
View File

@@ -108,7 +108,7 @@ def configure_visual_model(config: "PretrainedConfig") -> None:
Patches VLMs before loading them.
"""
model_type = getattr(config, "model_type", None)
if model_type == "llava": # required for ds zero3 and valuehead models
if model_type in ["llava", "llava_next", "video_llava", "idefics2", "llava_next_video"]: # required for ds zero3 and valuehead models
setattr(config, "hidden_size", getattr(config.text_config, "hidden_size", None))
if getattr(config, "is_yi_vl_derived_model", None):
@@ -150,7 +150,7 @@ def get_image_seqlen(config: "PretrainedConfig") -> int:
image_seqlen += 1
elif model_type == "paligemma":
image_seqlen = config.vision_config.num_image_tokens
elif model_type == "qwen2_vl": # variable length
else:
image_seqlen = -1
return image_seqlen