xinyun/DeepSeek-V3
1
0
Fork 0
mirror of https://git.datalinker.icu/deepseek-ai/DeepSeek-V3.git synced 2025-12-08 20:34:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge 328e6aaaa6ed1266ea36f0c53fe7ae228c868a69 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b

Browse Source
This commit is contained in:
Bruce-x-1997 2025-09-26 02:44:04 +00:00 committed by GitHub
commit 2b692199bc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
inference/configs/config_kimi_k2.json Normal file
View File

@ -0,0 +1,26 @@
{
"vocab_size": 163840,
"dim": 7168,
"inter_dim": 18432,
"moe_inter_dim": 2048,
"n_layers": 61,
"n_dense_layers": 1,
"n_heads": 64,
"n_routed_experts": 384,
"n_shared_experts": 1,
"n_activated_experts": 8,
"n_expert_groups": 1,
"n_limited_groups": 1,
"route_scale": 2.827,
"score_func": "sigmoid",
"q_lora_rank": 1536,
"kv_lora_rank": 512,
"qk_nope_head_dim": 128,
"qk_rope_head_dim": 64,
"v_head_dim": 128,
"dtype": "fp8",
"rope_theta": 50000.0,
"rope_factor": 64,
"beta_fast": 1,
"beta_slow": 1
}