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

fix constants

This commit is contained in:
BUAADreamer 2024-09-29 22:00:01 +08:00
parent 23916d57c1
commit 485fc04716
3 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llamafactory/extras/constants.py
View File

@ -896,7 +896,7 @@ register_model_group(
"LLaVA-NeXT-Video-7B-32k-Chat": {
DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-7B-32K-hf",
},
"LLaVA-NeXT-Video-7B-DPO": {
"LLaVA-NeXT-Video-7B-DPO-Chat": {
DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-7B-DPO-hf",
},
},
@ -910,7 +910,7 @@ register_model_group(
"LLaVA-NeXT-Video-Yi-34B-Chat": {
DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-34B-hf",
},
"LLaVA-NeXT-Video-Yi-34B-DPO": {
"LLaVA-NeXT-Video-Yi-34B-DPO-Chat": {
DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-34B-DPO-hf",
},
},

2
src/llamafactory/model/model_utils/misc.py
View File

@ -34,7 +34,7 @@ def find_all_linear_modules(model: "PreTrainedModel", freeze_vision_tower: bool)
forbidden_modules.add("output_layer")
elif model_type == "internlm2":
forbidden_modules.add("output")
elif model_type in ["llava", "paligemma", "video_llava"] or "llava_next" in model_type:
elif model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
forbidden_modules.add("multi_modal_projector")
elif model_type == "qwen2_vl":
forbidden_modules.add("merger")

16
src/llamafactory/model/model_utils/visual.py
View File

@ -92,7 +92,7 @@ def autocast_projector_dtype(model: "PreTrainedModel", model_args: "ModelArgumen
if getattr(model, "quantization_method", None):
model_type = getattr(model.config, "model_type", None)
if model_type in ["llava", "paligemma", "video_llava"] or "llava_next" in model_type:
if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
mm_projector: "torch.nn.Module" = getattr(model, "multi_modal_projector")
elif model_type == "qwen2_vl":
mm_projector: "torch.nn.Module" = getattr(getattr(model, "visual"), "merger")
@ -108,9 +108,13 @@ def configure_visual_model(config: "PretrainedConfig") -> None:
Patches VLMs before loading them.
"""
model_type = getattr(config, "model_type", None)
if (
model_type in ["llava", "video_llava"] or "llava_next" in model_type
): # required for ds zero3 and valuehead models
if model_type in [
"llava",
"llava_next",
"llava_next_video",
"paligemma",
"video_llava",
]: # 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):
@ -124,7 +128,7 @@ def get_forbidden_modules(config: "PretrainedConfig", finetuning_args: "Finetuni
"""
model_type = getattr(config, "model_type", None)
forbidden_modules = set()
if model_type in ["llava", "paligemma", "video_llava"] or "llava_next" in model_type:
if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
if finetuning_args.freeze_vision_tower:
forbidden_modules.add("vision_tower")
@ -182,7 +186,7 @@ def patch_target_modules(
"""
model_type = getattr(config, "model_type", None)
if finetuning_args.freeze_vision_tower:
if model_type in ["llava", "paligemma", "video_llava"] or "llava_next" in model_type:
if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
return "^(?!.*vision_tower).*(?:{}).*".format("|".join(target_modules))
elif model_type == "qwen2_vl":
return "^(?!.*visual).*(?:{}).*".format("|".join(target_modules))