Llama-2-7b-QTIP-2Bit / config.json
at676's picture
212a89e0317de84f894c3ff44ed308b1ef8ed4088be488a2bc9acc307ceab703
1fcc766 verified
raw
history blame
No virus
907 Bytes
{
"_name_or_path": "meta-llama/Llama-2-7b-hf",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"quip_params": {
"K": 2,
"L": 16,
"V": 2,
"codebook": "bitshift",
"codebook_version": 0,
"decode_mode": "quantlut_sym",
"td_x": 16,
"td_y": 16,
"tlut_bits": 9
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32000
}