Qwen3-32B-float8dq / config.json
jerryzh168's picture
Upload Qwen3ForCausalLM
0630155 verified
{
"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": 5120,
"initializer_range": 0.02,
"intermediate_size": 25600,
"max_position_embeddings": 40960,
"max_window_layers": 64,
"model_type": "qwen3",
"num_attention_heads": 64,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"quantization_config": {
"include_input_output_embeddings": false,
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"granularity": [
{
"_data": {},
"_type": "PerRow",
"_version": 1
},
{
"_data": {},
"_type": "PerRow",
"_version": 1
}
],
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 1
}
},
"quant_type_kwargs": {},
"untie_embedding_weights": false
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}