|
{ |
|
"_name_or_path": "/workspace/process/skywork_skywork-13b-base/source", |
|
"architectures": [ |
|
"SkyworkForCausalLM" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "configuration_skywork.SkyworkConfig", |
|
"AutoModelForCausalLM": "modeling_skywork.SkyworkForCausalLM" |
|
}, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4608, |
|
"initializer_range": 0.01, |
|
"intermediate_size": 12288, |
|
"max_position_embeddings": 131072, |
|
"model_type": "skywork", |
|
"num_attention_heads": 36, |
|
"num_hidden_layers": 52, |
|
"num_key_value_heads": 36, |
|
"pad_token_id": 0, |
|
"pretraining_tp": 1, |
|
"quantization_config": { |
|
"batch_size": 1, |
|
"bits": 4, |
|
"block_name_to_quantize": "model.layers", |
|
"damp_percent": 0.1, |
|
"desc_act": true, |
|
"disable_exllama": false, |
|
"group_size": 128, |
|
"max_input_length": null, |
|
"model_seqlen": 8192, |
|
"module_name_preceding_first_block": [ |
|
"model.embed_tokens" |
|
], |
|
"pad_token_id": null, |
|
"quant_method": "gptq", |
|
"sym": true, |
|
"tokenizer": null, |
|
"true_sequential": true, |
|
"use_cuda_fp16": true |
|
}, |
|
"rms_norm_eps": 1e-06, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.34.1", |
|
"use_cache": true, |
|
"vocab_size": 65519 |
|
} |