Text Generation
MLX
Safetensors
English
qwen3
Merge
programming
code generation
code
coding
coder
chat
brainstorm
qwen
qwencoder
brainstorm20x
esper
esper-3
valiant
valiant-labs
qwen-3
qwen-3-4b
4b
reasoning
code-instruct
python
javascript
dev-ops
jenkins
terraform
scripting
powershell
azure
aws
gcp
cloud
problem-solving
architect
engineer
developer
creative
analytical
expert
rationality
conversational
instruct
| { | |
| "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": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 55, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.0.dev0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } |