mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[Cherry-Pick] add mm token usage (#4648)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* [Feature] add mm token usage (#4570) * 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 * update doc * update doc --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
@@ -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)
|
||||
|
||||
Reference in New Issue
Block a user