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 13:42:53 +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

2
README.md
View File

@ -118,7 +118,7 @@ Compared to previous versions of DeepSeek-R1, the usage recommendations for Deep
1. System prompt is supported now.
2. It is not required to add "\<think\>\n" at the beginning of the output to force the model into thinking pattern.
The model architecture of DeepSeek-R1-0528-Qwen3-8B is identical to that of Qwen3-8B, but it shares the same tokenizer configuration as DeepSeek-R1-0528. This model can be run in the same manner as Qwen3-8B.
The model architecture of DeepSeek-R1-0528-Qwen3-8B is identical to that of Qwen3-8B, but it shares the same tokenizer configuration as DeepSeek-R1-0528. This model can be run in the same manner as Qwen3-8B, but it is essential to ensure that all configuration files are sourced from our repository rather than the original Qwen3 project.
### System Prompt
In the official DeepSeek web/app, we use the same system prompt with a specific date.

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,