Update README.md

README.md

@@ -13,7 +13,7 @@ tags:
 
 # **TimeLens-8B**
 
-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.
+> 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.
 
 ## TimeLens-8B [GGUF]
 
@@ -32,4 +32,13 @@ TimeLens-8B from TencentARC is an 8B-parameter multimodal vision-language model
 | TimeLens-8B.Q8_0.gguf | Q8_0 | 8.71 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.Q8_0.gguf) |
 | TimeLens-8B.f16.gguf | F16 | 16.4 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.f16.gguf) |
 | 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) |
-| TimeLens-8B.mmproj-f16.gguf | mmproj-f16 | 1.16 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.mmproj-f16.gguf) |
+| TimeLens-8B.mmproj-f16.gguf | mmproj-f16 | 1.16 GB | [Download](https://huggingface.co/prithivMLmods/TimeLens-8B/blob/main/TimeLens-8B.mmproj-f16.gguf) |
+
+## Quants Usage 
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)