| { |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "config_groups": { |
| "group_0": { |
| "input_activations": { |
| "num_bits": 8, |
| "strategy": "tensor", |
| "type": "float" |
| }, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "num_bits": 8, |
| "strategy": "tensor", |
| "type": "float" |
| } |
| } |
| }, |
| "eos_token_id": 151643, |
| "format": "naive-quantized", |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "ignore": [ |
| "lm_head" |
| ], |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "model_type": "qwen3", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 8, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "frozen", |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
|
|
