ai-models/DeepSeek-R1-0528-Qwen3-8B
2
0
Fork 0
mirror of https://www.modelscope.cn/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B.git synced 2026-04-02 21:52:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Small fix

Browse Source
This commit is contained in:
msr2000
2025-05-29 21:16:31 +08:00
parent c839598301
commit 5ee5fa4832
2 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
config.json
View File

@ -21,7 +21,8 @@
"rope_scaling": {
"rope_type": "yarn",
"factor": 4.0,
"original_max_position_embeddings": 32768
"original_max_position_embeddings": 32768,
"attn_factor": 0.8782488562869419
},
"rope_theta": 1000000,
"sliding_window": null,