93 lines
2.1 KiB
JSON
93 lines
2.1 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Qwen3ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 151643,
|
||
|
|
"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,
|
||
|
|
"quantization_config": {
|
||
|
|
"bits": 4,
|
||
|
|
"checkpoint_format": "gptq",
|
||
|
|
"desc_act": false,
|
||
|
|
"group_size": 128,
|
||
|
|
"hyb_act": false,
|
||
|
|
"lm_head": false,
|
||
|
|
"meta": {
|
||
|
|
"damp_auto_increment": 0.01,
|
||
|
|
"damp_percent": 0.05,
|
||
|
|
"mse": 0.0,
|
||
|
|
"quantizer": [
|
||
|
|
"gptqmodel:4.0.0"
|
||
|
|
],
|
||
|
|
"static_groups": false,
|
||
|
|
"true_sequential": true,
|
||
|
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
||
|
|
"v2": false,
|
||
|
|
"v2_alpha": 0.25
|
||
|
|
},
|
||
|
|
"pack_dtype": "int32",
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"sym": true
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 1000000,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.55.4",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|