apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 17:11:21 +08:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

[Feature] add mm token usage (#4570)

Browse Source 
* add mm token usage

* fix unit test

* fix unit test

* fix unit test

* fix model path

* fix unit test

* fix unit test

* fix unit test

* remove uncomment

* change var name

* fix code style

* fix code style

* fix code style

* fix code style

* fix unit test
This commit is contained in:
ApplEOFDiscord
2025-10-29 14:37:12 +08:00
committed by GitHub
parent fc5cd1adb1
commit 14f8cddaf1
9 changed files with 70 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/input/ernie4_5_vl_processor/process.py
+4
View File
@@ -193,6 +193,8 @@ class DataProcessor:
"labels": [],
"cur_position": 0,
"video_cnt": 0,
"num_input_image_tokens": 0,
"num_input_video_tokens": 0,
"mm_positions": [],
"mm_hashes": [],
}
@@ -357,6 +359,7 @@ class DataProcessor:
outputs["mm_positions"].append(ImagePosition(len(outputs["input_ids"]), num_tokens))
outputs["input_ids"].extend([self.image_patch_id] * num_tokens)
outputs["token_type_ids"].extend([IDS_TYPE_FLAG["image"]] * num_tokens)
outputs["num_input_image_tokens"] += num_tokens
pos_ids = self._compute_3d_positions(1, patches_h, patches_w, outputs["cur_position"])
outputs["position_ids"].extend(pos_ids)
@@ -428,6 +431,7 @@ class DataProcessor:
outputs["mm_positions"].append(ImagePosition(len(outputs["input_ids"]), num_tokens))
outputs["input_ids"].extend([self.image_patch_id] * num_tokens)
outputs["token_type_ids"].extend([IDS_TYPE_FLAG["video"]] * num_tokens)
outputs["num_input_video_tokens"] += num_tokens
pos_ids = self._compute_3d_positions(num_frames, patches_h, patches_w, outputs["cur_position"])
outputs["position_ids"].extend(pos_ids)