DeepSeek-V3/inference/configs/config_v3.1.json
youkaichao b15f0dbbbe
support scale_fmt=ue8m0 (#964)
* support scale_fmt=ue8m0

* keep improving

Signed-off-by: youkaichao <youkaichao@gmail.com>

* keep improving

Signed-off-by: youkaichao <youkaichao@gmail.com>

* add clamp min of 1e-4

Signed-off-by: youkaichao <youkaichao@gmail.com>

* rename config

Signed-off-by: youkaichao <youkaichao@gmail.com>

---------

Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-08-27 15:30:21 +08:00

23 lines
529 B
JSON

{
"vocab_size": 129280,
"dim": 7168,
"inter_dim": 18432,
"moe_inter_dim": 2048,
"n_layers": 61,
"n_dense_layers": 3,
"n_heads": 128,
"n_routed_experts": 256,
"n_shared_experts": 1,
"n_activated_experts": 8,
"n_expert_groups": 8,
"n_limited_groups": 4,
"route_scale": 2.5,
"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",
"scale_fmt": "ue8m0"
}