Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,6 @@ language:
|
|
| 6 |
- zh
|
| 7 |
base_model:
|
| 8 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
| 6 |
- zh
|
| 7 |
base_model:
|
| 8 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
DeepSeekR1蒸馏Qwen2.5 32B版本经过Int4 GPTQ Marlin算法量化的版本，推荐RTX4090 24GB 2块GPU推理，性能达到1700tokens/秒，最优并发128同时使用。比PF16版本性能相当，ceval评测82.3
|