christian.schwarz/DeepSeek-R1-Zero
1
0
Fork 0
mirror of https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero synced 2026-03-11 05:26:30 +01:00
Code Issues Packages Projects Releases Wiki Activity

Make config params float to avoid warning in Transformers

Browse Source
This commit is contained in:
Matthew Carrigan 2025-04-03 12:21:29 +00:00 committed by system
parent 72234287cb
commit 4601822cdd
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
config.json
View File

@ -45,9 +45,9 @@
},
"rms_norm_eps": 1e-06,
"rope_scaling": {
"beta_fast": 32,
"beta_slow": 1,
"factor": 40,
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 40.0,
"mscale": 1.0,
"mscale_all_dim": 1.0,
"original_max_position_embeddings": 4096,