| { | |
| "_name_or_path": "1bitLLM/bitnet_b1_58-3B", | |
| "architectures": [ | |
| "BitnetForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "group_size": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3200, | |
| "initializer_range": 0.02, | |
| "input_bits": 8, | |
| "intermediate_size": 8640, | |
| "max_position_embeddings": 2048, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 32000, | |
| "pretraining_tp": 1, | |
| "quant_bits": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.39.2", | |
| "use_cache": true, | |
| "vocab_size": 32002, | |
| "weight_bits": 1 | |
| } | |