Update README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,34 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- TencentARC/TimeLens-8B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# **TimeLens-8B**
|
| 8 |
|
| 9 |
-
TimeLens-8B from TencentARC is an 8B-parameter multimodal vision-language model fine-tuned from Qwen3-VL-8B-Instruct using a novel RLVR (reinforcement learning with verifiable rewards) recipe on the high-quality TimeLens-100K VTG dataset, achieving state-of-the-art video temporal grounding performance among open-source models with 72.0% R1@0.3 (Charades-TimeLens), 64.5% R1@0.3 (ActivityNet-TimeLens), and 75.6% R1@0.3 (QVHighlights-TimeLens), significantly outperforming baselines like Qwen3-VL-8B-Instruct and Qwen2.5-VL-7B. Designed for precise localization of visual events described by natural language queries, it outputs timestamped segments in the format "The event happens in <start time> - <end time> seconds" using low FPS=2 sampling (min_pixels=642828, total_pixels=143362828) for efficient video processing via Transformers with Flash-Attention-2 support. Released with code, project page, and TimeLens-Bench evaluation suite, it excels on Charades-TimeLens, ActivityNet-TimeLens, and QVHighlights-TimeLens leaderboards for research in video understanding, temporal reasoning, and event detection.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model:
|
| 4 |
- TencentARC/TimeLens-8B
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: image-text-to-text
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- text-generation-inference
|
| 11 |
+
- llama.cpp
|
| 12 |
---
|
| 13 |
|
| 14 |
# **TimeLens-8B**
|
| 15 |
|
| 16 |
+
TimeLens-8B from TencentARC is an 8B-parameter multimodal vision-language model fine-tuned from Qwen3-VL-8B-Instruct using a novel RLVR (reinforcement learning with verifiable rewards) recipe on the high-quality TimeLens-100K VTG dataset, achieving state-of-the-art video temporal grounding performance among open-source models with 72.0% R1@0.3 (Charades-TimeLens), 64.5% R1@0.3 (ActivityNet-TimeLens), and 75.6% R1@0.3 (QVHighlights-TimeLens), significantly outperforming baselines like Qwen3-VL-8B-Instruct and Qwen2.5-VL-7B. Designed for precise localization of visual events described by natural language queries, it outputs timestamped segments in the format "The event happens in <start time> - <end time> seconds" using low FPS=2 sampling (min_pixels=642828, total_pixels=143362828) for efficient video processing via Transformers with Flash-Attention-2 support. Released with code, project page, and TimeLens-Bench evaluation suite, it excels on Charades-TimeLens, ActivityNet-TimeLens, and QVHighlights-TimeLens leaderboards for research in video understanding, temporal reasoning, and event detection.
|
| 17 |
+
|
| 18 |
+
## TimeLens-8B [GGUF]
|
| 19 |
+
|
| 20 |
+
| File Name | Quant Type | File Size | File Link |
|
| 21 |
+
| - | - | - | - |
|
| 22 |
+
| TimeLens-8B.IQ4_XS.gguf | IQ4_XS | 4.59 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.IQ4_XS.gguf) |
|
| 23 |
+
| TimeLens-8B.Q2_K.gguf | Q2_K | 3.28 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q2_K.gguf) |
|
| 24 |
+
| TimeLens-8B.Q3_K_L.gguf | Q3_K_L | 4.43 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q3_K_L.gguf) |
|
| 25 |
+
| TimeLens-8B.Q3_K_M.gguf | Q3_K_M | 4.12 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q3_K_M.gguf) |
|
| 26 |
+
| TimeLens-8B.Q3_K_S.gguf | Q3_K_S | 3.77 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q3_K_S.gguf) |
|
| 27 |
+
| TimeLens-8B.Q4_K_M.gguf | Q4_K_M | 5.03 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q4_K_M.gguf) |
|
| 28 |
+
| TimeLens-8B.Q4_K_S.gguf | Q4_K_S | 4.8 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q4_K_S.gguf) |
|
| 29 |
+
| TimeLens-8B.Q5_K_M.gguf | Q5_K_M | 5.85 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q5_K_M.gguf) |
|
| 30 |
+
| TimeLens-8B.Q5_K_S.gguf | Q5_K_S | 5.72 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q5_K_S.gguf) |
|
| 31 |
+
| TimeLens-8B.Q6_K.gguf | Q6_K | 6.73 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q6_K.gguf) |
|
| 32 |
+
| TimeLens-8B.Q8_0.gguf | Q8_0 | 8.71 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q8_0.gguf) |
|
| 33 |
+
| TimeLens-8B.f16.gguf | F16 | 16.4 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.f16.gguf) |
|
| 34 |
+
| TimeLens-8B.mmproj-Q8_0.gguf | mmproj-Q8_0 | 752 MB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.mmproj-Q8_0.gguf) |
|
| 35 |
+
| TimeLens-8B.mmproj-f16.gguf | mmproj-f16 | 1.16 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.mmproj-f16.gguf) |
|