Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -6,8 +6,8 @@ language:
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Introduction
|
| 9 |
-
Zhipu officially released its next-generation open-source flagship model **GLM-5.2**, the latest flagship targeting **Long Horizon Tasks**. Compared to its predecessor GLM-5.1, it achieves a significant leap in long-horizon task capabilities and is open-sourced under the **MIT License**. The **FlagOS Zhongzhi Community** completed multi-chip adaptation and inference deployment at the first opportunity, currently covering
|
| 10 |
-
**
|
| 11 |
|
| 12 |
Developers can rapidly deploy via the FlagOS unified, open-source software stack; model files and deployment guides are simultaneously available on **ModelScope** and **HuggingFace**. GLM-5.2 is a model featuring a stable and usable **1M context window**, purpose-built for Long Horizon Tasks. Its core capabilities include:
|
| 13 |
|
|
@@ -28,9 +28,8 @@ Developers can rapidly deploy via the FlagOS unified, open-source software stack
|
|
| 28 |
## Benchmark Result
|
| 29 |
| Metrics | GLM-5.2-Nvidia-Origin | GLM-5.2-Mthreads-FlagOS |
|
| 30 |
|--------------|--------------------------------|-------------------------|
|
| 31 |
-
| GPQA_Diamond |
|
| 32 |
-
| musr_generative |
|
| 33 |
-
# User Guide
|
| 34 |
Environment Setup
|
| 35 |
|
| 36 |
| Item | Version |
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Introduction
|
| 9 |
+
Zhipu officially released its next-generation open-source flagship model **GLM-5.2**, the latest flagship targeting **Long Horizon Tasks**. Compared to its predecessor GLM-5.1, it achieves a significant leap in long-horizon task capabilities and is open-sourced under the **MIT License**. The **FlagOS Zhongzhi Community** completed multi-chip adaptation and inference deployment at the first opportunity, currently covering four chips:
|
| 10 |
+
**Moore Threads S5000, T-Head 810E, Metax C550 and Hygon DCU BW1000**.
|
| 11 |
|
| 12 |
Developers can rapidly deploy via the FlagOS unified, open-source software stack; model files and deployment guides are simultaneously available on **ModelScope** and **HuggingFace**. GLM-5.2 is a model featuring a stable and usable **1M context window**, purpose-built for Long Horizon Tasks. Its core capabilities include:
|
| 13 |
|
|
|
|
| 28 |
## Benchmark Result
|
| 29 |
| Metrics | GLM-5.2-Nvidia-Origin | GLM-5.2-Mthreads-FlagOS |
|
| 30 |
|--------------|--------------------------------|-------------------------|
|
| 31 |
+
| GPQA_Diamond | 85.85 | Evaluating |
|
| 32 |
+
| musr_generative | 69.2 | 67.2 |
|
|
|
|
| 33 |
Environment Setup
|
| 34 |
|
| 35 |
| Item | Version |
|