| { |
| "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_config": { |
| "config_groups": { |
| "config_group_0": { |
| "format": "nvfp4-pack-quantized", |
| "input_activations": { |
| "dynamic": "local", |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "static_minmax", |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float" |
| }, |
| "output_activations": null, |
| "targets": [ |
| "re:.*mlp.*\\.(gate_up|gate|up|down)_proj$", |
| "re:.*self_attn.*\\.(q|k|v|o)_proj$" |
| ], |
| "weights": { |
| "dynamic": false, |
| "group_size": 16, |
| "num_bits": 4, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float" |
| } |
| } |
| }, |
| "format": "nvfp4-pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [], |
| "kv_cache_scheme": { |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "strategy": "tensor", |
| "symmetric": true, |
| "type": "float" |
| }, |
| "moe_sparsity_config": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "version": "0.19.1a20261023" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.1", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
