bitnet-5B-v1 / config.json
Ttimofeyka's picture
Upload config.json with huggingface_hub
f5361f4 verified
raw
history blame
768 Bytes
{
"_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,
"hidden_act": "silu",
"hidden_size": 3200,
"initializer_range": 0.02,
"input_bits": 8,
"intermediate_size": 8640,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 32,
"pad_token_id": 32000,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 32002,
"weight_bits": 1
}