GLM-5.3-Flash-DFlash2 / config.json
voipmonitor's picture
Publish MXFP8 DFlash2 checkpoint
cadcd59 verified
Raw
History Blame Contribute Delete
1.57 kB
{
"architectures": [
"DFlash2DraftModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dflash_config": {
"block_size": 8,
"conv_group_size": 16,
"conv_kernel_size": 2,
"mask_token_id": 154856,
"selector_rank": 256,
"selector_top_k": 16,
"target_layer_ids": [
5,
14,
24,
33,
42
]
},
"dtype": "bfloat16",
"eos_token_id": [
154820,
154827,
154829
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"is_causal": false,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 1048576,
"max_window_layers": 5,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 5,
"num_key_value_heads": 8,
"num_target_layers": 45,
"pad_token_id": 154820,
"quantization_config": {
"producer": {
"name": "glm53-dflash2-mxfp8-converter",
"version": 1
},
"quant_method": "modelopt",
"quantization": {
"exclude_modules": [
"lm_head"
],
"kv_cache_quant_algo": null,
"quant_algo": "MXFP8"
}
},
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"sliding_window": 2048,
"tie_word_embeddings": false,
"transformers_version": "5.7.0",
"use_cache": false,
"use_sliding_window": true,
"vocab_size": 154880
}