Text Generation
MLX
Safetensors
qwen3
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
finetune
brainstorm 20x
brainstorm
optional thinking
creative
all use cases
QiMing
QiMing-holos
bagua
decision-making
strategic-analysis
cognitive-architecture
philosophy-driven-ai
conversational
{ | |
"architectures": [ | |
"Qwen3ForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 151643, | |
"eos_token_id": 151645, | |
"head_dim": 128, | |
"hidden_act": "silu", | |
"hidden_size": 5120, | |
"initializer_range": 0.02, | |
"intermediate_size": 17408, | |
"layer_types": [ | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention", | |
"full_attention" | |
], | |
"max_position_embeddings": 40960, | |
"max_window_layers": 40, | |
"model_type": "qwen3", | |
"num_attention_heads": 40, | |
"num_hidden_layers": 59, | |
"num_key_value_heads": 8, | |
"rms_norm_eps": 1e-06, | |
"rope_scaling": null, | |
"rope_theta": 1000000, | |
"sliding_window": null, | |
"tie_word_embeddings": false, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.55.0", | |
"use_cache": true, | |
"use_sliding_window": false, | |
"vocab_size": 151936 | |
} |