Upload folder using huggingface_hub

README.md

@@ -72,7 +72,7 @@ MOSS-VL utilizes Cross-attention Rotary Position Embedding (XRoPE), tailored to
 
 ## 📊 Model Performance
 
-We conducted a comprehensive evaluation of **MOSS-VL-Instruct-0408** across four key dimensions: Multimodal Perception, Document/OCR, Multimodal Reasoning, and Video Understanding. The results demonstrate that MOSS-VL achieves outstanding performance, particularly excelling in **general multimodal perception** and **complex video analysis**.
+We conducted a comprehensive evaluation of **MOSS-VL-Instruct-0408** across four key dimensions: Multimodal Perception, Multimodal Reasoning, Document/OCR, and Video Understanding. The results demonstrate that MOSS-VL achieves outstanding performance, particularly excelling in **general multimodal perception** and **complex video analysis**.
 
 ### 🌟 Key Highlights
 
@@ -99,6 +99,11 @@ conda activate moss_vl
 pip install -i https://pypi.org/simple --no-build-isolation -r requirements.txt
 ```
 
+Validated setup notes:
+
+- CUDA runtime used for validation: `12.8`
+- Inference loading uses `trust_remote_code=True` and `attn_implementation="flash_attention_2"`
+
 ### 🏃 Run Inference
 
 
@@ -288,7 +293,7 @@ texts = [item["text"] for item in result["results"]]
 
 MOSS-VL-Instruct-0408 represents an early milestone in the MOSS-VL roadmap, and we're actively working on several directions to push it further:
 
-- 🧮 **Math & Code Reasoning** — While the current checkpoint already exhibits solid general reasoning, we plan to substantially strengthen its mathematical reasoning and code understanding capabilities, especially in multimodal contexts (e.g., reasoning over diagrams, charts, screenshots, and code-bearing visual inputs).
+- 🧮 **Math & Code Reasoning** — While the current checkpoint already exhibits solid general reasoning, we plan to substantially strengthen its mathematical reasoning and code reasoning capabilities, especially in multimodal contexts.
 - ⚡ **Real-Time Streaming Variant** — The upcoming **MOSS-VL-RealTime** checkpoint will extend MOSS-VL to low-latency, streaming video understanding, enabling interactive applications such as live video chat, real-time event detection, and online assistants — complementing this offline checkpoint.
 - 🎯 **RL Post-Training** — We are working on a reinforcement learning post-training stage to further align the model with human preferences and to unlock stronger multi-step reasoning behaviors on top of the SFT foundation.
 - ⏳ **Longer Context for Hour-Scale Video** — Continuing to push context scaling so the model can comfortably handle hour-scale and multi-hour videos with consistent temporal grounding.