Text Generation
Transformers
Safetensors
MLX
English
qwen3
shining-valiant
shining-valiant-3
valiant
valiant-labs
qwen
qwen-3
qwen-3-8b
8b
reasoning
code
code-reasoning
science
science-reasoning
physics
biology
chemistry
earth-science
astronomy
machine-learning
artificial-intelligence
compsci
computer-science
information-theory
ML-Ops
math
cuda
deep-learning
agentic
LLM
neuromorphic
self-improvement
complex-systems
cognition
linguistics
philosophy
logic
epistemology
simulation
game-theory
knowledge-management
creativity
problem-solving
architect
engineer
developer
creative
analytical
expert
rationality
conversational
chat
instruct
mlx-my-repo
text-generation-inference
4-bit precision
| { | |
| "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": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "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" | |
| ], | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.53.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } |