Qwen3-4B-NPU2 / config.json
FastFlowLM's picture
Update config.json
86b0c5c verified
raw
history blame
851 Bytes
{
"model_type": "qwen3",
"vocab_size": 151936,
"max_position_embeddings": 40960,
"hidden_size": 2560,
"intermediate_size": 9728,
"num_hidden_layers": 36,
"num_attention_heads": 32,
"use_sliding_window": false,
"sliding_window": null,
"max_window_layers": 36,
"num_key_value_heads": 8,
"head_dim": 128,
"hidden_act": "silu",
"initializer_range": 0.02,
"rms_norm_eps": 1e-06,
"use_cache": true,
"rope_theta": 1000000,
"rope_scaling": null,
"attention_bias": false,
"attention_dropout": 0.0,
"architectures": [
"LlamaForCausalLM"
],
"torch_dtype": "bfloat16",
"transformers_version": "4.45.0.dev0",
"use_cache": true,
"addr_qk": 9216,
"addr_kv": 34816,
"addr_l_begin_mha": 54272,
"addr_l_end_mha": 25600,
"addr_kk": 45056,
"flm_version": "0.1.8"
}