ALTICDEV's picture
Upload corrected Mini V24 artifacts
26f9b89 verified
Raw History Blame Contribute Delete
2.76 kB
{
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"image_token_id": 98290,
"model_name": "qwen35-2b-v23-step7314",
"model_type": "qwen3_5",
"quantization": {
"bits": 6,
"group_size": 64,
"mode": "affine"
},
"quantization_config": {
"bits": 6,
"group_size": 64,
"mode": "affine"
},
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"dtype": "bfloat16",
"eos_token_id": 98278,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"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_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 16,
"linear_value_head_dim": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 8,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"partial_rotary_factor": 0.25,
"rope_theta": 10000000,
"type": "default"
},
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 98304
},
"tie_word_embeddings": true,
"transformers_version": "4.57.0.dev0",
"video_token_id": 98291,
"vision_end_token_id": 98288,
"vision_start_token_id": 98287,
"dflash_config": {
"block_size": 8,
"mask_token_id": 98278,
"target_layer_ids": [
2,
7,
12,
17,
21
],
"draft_vocab_size": 98304,
"num_layers": 5,
"vocabulary_source": "target",
"attention_head_count": 8,
"attention_kv_head_count": 2,
"head_dimension": 256,
"sliding_window": 2048,
"quantization": {
"bits": 6,
"group_size": 64,
"mode": "affine"
},
"sliding_window_non_causal": false
}
}