Quantised-Phi-2 / config.json
Adithya Vardan
Upload 10 files
c579e94 verified
{
"_name_or_path": "microsoft/phi-2",
"architectures": [
"PhiForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
},
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"hidden_act": "gelu_new",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 10240,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "phi",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"partial_rotary_factor": 0.4,
"qk_layernorm": false,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": "model.layers",
"damp_percent": 0.1,
"dataset": "wikitext2",
"desc_act": false,
"disable_exllama": true,
"group_size": 128,
"model_seqlen": 4096,
"module_name_preceding_first_block": [
"model.embed_tokens",
"model.embed_dropout"
],
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"true_sequential": true,
"use_cuda_fp16": true
},
"resid_pdrop": 0.1,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.39.0",
"use_cache": true,
"vocab_size": 51200
}