121 lines
2.8 KiB
JSON
121 lines
2.8 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Qwen3ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": null,
|
||
|
|
"dtype": "float16",
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 2560,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 9728,
|
||
|
|
"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": 262144,
|
||
|
|
"max_window_layers": 36,
|
||
|
|
"model_type": "qwen3",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 36,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 151654,
|
||
|
|
"quantization_config": {
|
||
|
|
"bits": 4,
|
||
|
|
"checkpoint_format": "gptq",
|
||
|
|
"desc_act": false,
|
||
|
|
"format": "gptq",
|
||
|
|
"group_size": 128,
|
||
|
|
"lm_head": false,
|
||
|
|
"meta": {
|
||
|
|
"act_group_aware": true,
|
||
|
|
"auto_forward_data_parallel": true,
|
||
|
|
"damp_auto_increment": 0.01,
|
||
|
|
"damp_percent": 0.1,
|
||
|
|
"dense_vram_strategy": "exclusive",
|
||
|
|
"dense_vram_strategy_devices": null,
|
||
|
|
"fallback": {
|
||
|
|
"smooth": null,
|
||
|
|
"strategy": "rtn",
|
||
|
|
"threshold": "0.5%"
|
||
|
|
},
|
||
|
|
"foem": null,
|
||
|
|
"gc_mode": "interval",
|
||
|
|
"gptaq": null,
|
||
|
|
"hessian": {
|
||
|
|
"chunk_bytes": null,
|
||
|
|
"chunk_size": null,
|
||
|
|
"staging_dtype": "float32"
|
||
|
|
},
|
||
|
|
"mock_quantization": false,
|
||
|
|
"moe_vram_strategy": "exclusive",
|
||
|
|
"moe_vram_strategy_devices": null,
|
||
|
|
"mse": 0.0,
|
||
|
|
"offload_to_disk": true,
|
||
|
|
"offload_to_disk_path": "/tmp/gptqmodel_pf205jdd",
|
||
|
|
"pack_impl": "cpu",
|
||
|
|
"quantizer": [
|
||
|
|
"gptqmodel:7.1.0"
|
||
|
|
],
|
||
|
|
"static_groups": false,
|
||
|
|
"true_sequential": true,
|
||
|
|
"uri": "https://github.com/modelcloud/gptqmodel",
|
||
|
|
"wait_for_submodule_finalizers": false
|
||
|
|
},
|
||
|
|
"method": "gptq",
|
||
|
|
"pack_dtype": "int32",
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"sym": true
|
||
|
|
},
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_parameters": {
|
||
|
|
"rope_theta": 5000000,
|
||
|
|
"rope_type": "default"
|
||
|
|
},
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"transformers_version": "5.14.1",
|
||
|
|
"unsloth_fixed": true,
|
||
|
|
"unsloth_version": "2026.7.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 151936
|
||
|
|
}
|