1bitLLM/bitnet_b1_58-large
1292.5k
1{2 "_name_or_path": "1bitLLM/bitnet_b1_58-large",3 "architectures": [4 "BitnetForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 1,9 "eos_token_id": 2,10 "hidden_act": "silu",11 "hidden_size": 1536,12 "initializer_range": 0.02,13 "input_bits": 8,14 "intermediate_size": 4096,15 "max_position_embeddings": 2048,16 "model_type": "llama",17 "num_attention_heads": 16,18 "num_hidden_layers": 24,19 "num_key_value_heads": 16,20 "pad_token_id": 32000,21 "pretraining_tp": 1,22 "rms_norm_eps": 1e-05,23 "rope_scaling": null,24 "rope_theta": 10000.0,25 "tie_word_embeddings": true,26 "torch_dtype": "float16",27 "transformers_version": "4.39.0",28 "use_cache": true,29 "vocab_size": 32002,30 "weight_bits": 131}32 