aryan5v's picture
Add NVFP4 text encoder
3964e7f verified
Raw History Blame Contribute Delete
1.93 kB
{
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"image_token_id": 151655,
"model_type": "qwen3_vl",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 25600,
"max_position_embeddings": 262144,
"model_type": "qwen3_vl_text",
"num_attention_heads": 64,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_interleaved": true,
"mrope_section": [
24,
20,
20
],
"rope_type": "default"
},
"rope_theta": 5000000,
"use_cache": true,
"vocab_size": 151936
},
"tie_word_embeddings": false,
"transformers_version": "4.57.0.dev0",
"video_token_id": 151656,
"vision_config": {
"deepstack_visual_indexes": [
8,
16,
24
],
"depth": 27,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen3_vl",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 5120,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"num_hidden_layers_override": 50,
"quantization_config": {
"quant_method": "nvfp4",
"activation_scheme": "dynamic",
"fmt": "e2m1",
"group_size": 16,
"scale_fmt": "e4m3",
"scale_layout": "128x4",
"modules_to_not_convert": [
"model.visual",
"lm_head"
],
"producer": {
"converter": "convert_minimax_h3_text_encoder_nvfp4.py",
"flashinfer": "0.7.1rc2",
"kept_language_layers": 50
}
}
}