Commit 25108648 authored by raojy's avatar raojy 💬
Browse files

Update config.json

parent 2b50610e
{ {
"architectures": [ "architectures": [
"DeepseekV3ForCausalLM" "DeepseekV32ForCausalLM"
], ],
"attention_bias": false, "attention_bias": false,
"attention_dropout": 0.0, "attention_dropout": 0.0,
...@@ -17,7 +17,7 @@ ...@@ -17,7 +17,7 @@
"intermediate_size": 18432, "intermediate_size": 18432,
"kv_lora_rank": 512, "kv_lora_rank": 512,
"max_position_embeddings": 163840, "max_position_embeddings": 163840,
"model_type": "deepseek_v3", "model_type": "deepseek_v32",
"moe_intermediate_size": 2048, "moe_intermediate_size": 2048,
"moe_layer_freq": 1, "moe_layer_freq": 1,
"n_group": 8, "n_group": 8,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment