| { |
| "architectures": [ |
| "BitNetForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_bitnet.BitNetConfig", |
| "AutoModelForCausalLM": "modeling_bitnet.BitNetForCausalLM" |
| }, |
| "bos_token_id": 128000, |
| "dtype": "float32", |
| "eos_token_id": 128001, |
| "hidden_act": "relu2", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 6912, |
| "max_position_embeddings": 4096, |
| "model_type": "bitnet", |
| "num_attention_heads": 20, |
| "num_hidden_layers": 30, |
| "num_key_value_heads": 5, |
| "quantization_config": { |
| "linear_class": "autobitlinear", |
| "modules_to_not_convert": null, |
| "quant_method": "bitnet", |
| "quantization_mode": "online", |
| "rms_norm_eps": 1e-06, |
| "use_rms_norm": false |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": true, |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|