Video-Text-to-Text
Transformers
Safetensors
English
videochat_flash_qwen
feature-extraction
multimodal
custom_code
Eval Results (legacy)
Instructions to use OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update modeling_videochat_flash.py
Browse files
modeling_videochat_flash.py
CHANGED
|
@@ -679,7 +679,7 @@ class VideoChatFlashQwenForCausalLM(LlavaMetaForCausalLM, Qwen2ForCausalLM_Flash
|
|
| 679 |
|
| 680 |
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
|
| 681 |
if outputs.endswith(stop_str):
|
| 682 |
-
|
| 683 |
|
| 684 |
outputs = outputs.strip()
|
| 685 |
|
|
|
|
| 679 |
|
| 680 |
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
|
| 681 |
if outputs.endswith(stop_str):
|
| 682 |
+
outputs = outputs[: -len(stop_str)]
|
| 683 |
|
| 684 |
outputs = outputs.strip()
|
| 685 |
|