Files
octen-embedding-8b-w4a16/config.json
ModelHub XC 80d1d43641 初始化项目,由ModelHub XC社区提供模型
Model: groxaxo/octen-embedding-8b-w4a16
Source: Original Platform
2026-08-21 08:35:12 +08:00

87 lines
1.9 KiB
JSON

{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "float32",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": null,
"quantization_config": {
"amp": false,
"autoround_version": "0.12.2",
"batch_size": 1,
"bits": 4,
"data_type": "int",
"gradient_accumulate_steps": 8,
"group_size": 128,
"low_gpu_mem_usage": true,
"nsamples": 8,
"packing_format": "auto_round:auto_gptq",
"quant_method": "auto-round",
"seqlen": 512,
"sym": true
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.6.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151665
}