| { | |
| "architectures": [ | |
| "FP8Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_fp8_qwen3.FP8Qwen3Config", | |
| "AutoModel": "modeling_fp8_qwen3.FP8Qwen3Model", | |
| "AutoModelForCausalLM": "modeling_fp8_qwen3.FP8Qwen3ForCausalLM", | |
| "AutoModelForQuestionAnswering": "modeling_fp8_qwen3.FP8Qwen3ForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "modeling_fp8_qwen3.FP8Qwen3ForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_fp8_qwen3.FP8Qwen3ForTokenClassification" | |
| }, | |
| "bos_token_id": 151643, | |
| "dtype": "float8_e4m3fn", | |
| "eos_token_id": 151645, | |
| "fp8_config": { | |
| "act_block_size": 16, | |
| "float8_dtype": "torch.float8_e4m3fn", | |
| "layer_name": "", | |
| "mm_block_size": 128, | |
| "quant_type": "DIV", | |
| "training_mode": false | |
| }, | |
| "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_name_orig": "Qwen/Qwen3-8B", | |
| "model_name_quant": null, | |
| "model_type": "fp8_qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |