phixtral-4x2_8-GPTQ / config.json
TheBloke's picture
GPTQ model commit
fd79b68 verified
raw
history blame
1.66 kB
{
"_name_or_path": "/workspace/process/mlabonne_phixtral-4x2_8/source",
"activation_function": "gelu_new",
"architectures": [
"PhiForCausalLM"
],
"attn_pdrop": 0.0,
"auto_map": {
"AutoConfig": "configuration_phi.PhiConfig",
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
},
"embd_pdrop": 0.0,
"flash_attn": false,
"flash_rotary": false,
"fused_dense": false,
"img_processor": null,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "phi-msft",
"n_embd": 2560,
"n_head": 32,
"n_head_kv": null,
"n_inner": null,
"n_layer": 32,
"n_positions": 2048,
"num_experts_per_tok": 2,
"num_local_experts": 4,
"pad_token_id": 0,
"pretraining_tp": 1,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": null,
"cache_block_outputs": true,
"damp_percent": 0.1,
"desc_act": true,
"exllama_config": {
"version": 1
},
"group_size": 128,
"max_input_length": null,
"model_seqlen": null,
"module_name_preceding_first_block": null,
"modules_in_block_to_quantize": null,
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": false,
"use_exllama": true
},
"resid_pdrop": 0.1,
"rotary_dim": 32,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.0.dev0",
"use_cache": true,
"vocab_size": 51200
}