106 lines
2.4 KiB
JSON
106 lines
2.4 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 17408,
|
|
"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",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention"
|
|
],
|
|
"max_position_embeddings": 40960,
|
|
"max_window_layers": 40,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 40,
|
|
"num_key_value_heads": 8,
|
|
"quantization_config": {
|
|
"config_groups": {
|
|
"group_0": {
|
|
"format": "pack-quantized",
|
|
"input_activations": null,
|
|
"output_activations": null,
|
|
"targets": [
|
|
"Linear"
|
|
],
|
|
"weights": {
|
|
"actorder": null,
|
|
"block_structure": null,
|
|
"dynamic": false,
|
|
"group_size": 32,
|
|
"num_bits": 4,
|
|
"observer": "mse",
|
|
"observer_kwargs": {},
|
|
"strategy": "group",
|
|
"symmetric": true,
|
|
"type": "int"
|
|
}
|
|
}
|
|
},
|
|
"format": "pack-quantized",
|
|
"global_compression_ratio": null,
|
|
"ignore": [
|
|
"lm_head"
|
|
],
|
|
"kv_cache_scheme": null,
|
|
"quant_method": "compressed-tensors",
|
|
"quantization_status": "compressed",
|
|
"sparsity_config": {},
|
|
"transform_config": {},
|
|
"version": "0.10.3.dev47+ge463fe6"
|
|
},
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "4.57.0.dev0",
|
|
"use_cache": false,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
} |