初始化项目,由ModelHub XC社区提供模型
Model: DeepBrainz/DeepBrainz-R1-4B Source: Original Platform
This commit is contained in:
22
config.json
Normal file
22
config.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"hidden_size": 2560,
|
||||
"intermediate_size": 9728,
|
||||
"num_hidden_layers": 36,
|
||||
"num_attention_heads": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"head_dim": 128,
|
||||
"vocab_size": 151936,
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"model_type": "qwen3",
|
||||
"max_position_embeddings": 32768,
|
||||
"torch_dtype": "bfloat16",
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"tie_word_embeddings": false,
|
||||
"rope_scaling": {
|
||||
"type": "dynamic",
|
||||
"factor": 2.0
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user