charaf/ qwen3-vl-embedding-8b:latest

1 8 hours ago

vision tools thinking
... /
json
65de005735c0 · 1.5kB
{
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"dtype": "bfloat16",
"image_token_id": 151655,
"model_type": "qwen3_vl",
"quantization": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"quantization_config": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"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": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 262144,
"model_type": "qwen3_vl_text",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"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
},
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"use_cache": false,
"video_token_id": 151656,
"vision_end_token_id": 151653,
"vision_start_token_id": 151652
}