qwen3.8-flash-next:125b-a6b-nvfp4

18 5 hours ago

This experimental preview of the architecture that will underpin Qwen4.

vision tools thinking
... /
json
889658f2508e · 4.7kB
{
"architectures": [
"Qwen4ExpForConditionalGeneration"
],
"image_token_id": 248056,
"language_model_only": false,
"model_type": "qwen4_exp",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 248044,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"hc_count": 4,
"hc_lowrank": 320,
"head_dim": 256,
"heads_per_ngram": 8,
"hidden_act": "silu",
"hidden_size": 2560,
"indexer_budget": 2048,
"indexer_compress_ratio": 4,
"indexer_head_dim": 128,
"indexer_kv_heads": 1,
"indexer_n_heads": 4,
"initializer_range": 0.02,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 48,
"linear_value_head_dim": 128,
"make_ngram_vocab_size_divisible_by": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"model_type": "qwen4_exp_text",
"moe_intermediate_size": 640,
"mtp": {
"hybrid": true,
"layer_types": [
"full_attention"
],
"mtp_use_hidden_state_from_layer": null,
"num_hidden_layers": 1,
"rope_theta": 10000000
},
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"ngram_size": 3,
"ngram_vocab_size_base": 20000000,
"num_attention_heads": 24,
"num_experts": 512,
"num_experts_per_tok": 10,
"num_hidden_layers": 48,
"num_key_value_heads": 2,
"output_gate_type": "sigmoid",
"output_router_logits": false,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"ple_conv_kernel_size": 4,
"ple_embed_dim": 2560,
"ple_layer_ids": [
2
],
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"partial_rotary_factor": 0.25,
"rope_theta": 10000000,
"rope_type": "default"
},
"router_aux_loss_coef": 0.001,
"shared_expert_intermediate_size": 640,
"split_ngram_parts": 128,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 248320
},
"tie_word_embeddings": false,
"transformers_version": "5.8.0.dev0",
"video_token_id": 248057,
"vision_config": {
"deepstack_visual_indexes": [],
"depth": 27,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen4_exp",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 2560,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
}