WaveCut's picture
MOSS-Image-SFT OrbitQuant W4A8: transformer and text encoder with GPTQ rounding
3d73458 verified
Raw History Blame Contribute Delete
3.11 kB
{
"architectures": [
"Qwen3_5TextModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"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_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"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": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"pad_token_id": null,
"quantization_config": {
"activation_bits": 4,
"activation_eps": 1e-10,
"activation_kernel_backend": "auto",
"activation_norm_dtype": "float32",
"adaln_group_size": 64,
"adaln_policy": "int4_rtn",
"artifact_format_version": 1,
"block_size": "paper",
"codebook": "lloyd_max",
"codebook_dtype": "float32",
"codebook_version": 2,
"fused_layout": null,
"lowbit_boundary_protection": "auto",
"lowbit_interior_protection": "auto",
"lowbit_protected_bits": 4,
"lowbit_protected_blocks": 4,
"modules_dtype_dict": {},
"modules_to_convert": [],
"modules_to_not_convert": [
"in_proj_a",
"in_proj_b"
],
"modules_to_use_adaln": [],
"packed_matmul_block_k": 128,
"packed_matmul_block_m": 64,
"packed_matmul_block_n": 64,
"packed_matmul_num_warps": 4,
"quant_method": "orbitquant",
"rotation": "rpbh",
"rotation_seed": 0,
"row_norm_dtype": "bfloat16",
"runtime_mode": "auto_fused",
"target_policy": "universal",
"w4a4_int8_weight_cache": false,
"weight_bits": 4,
"weight_pack_dtype": "uint8",
"weight_row_tile_size": 256
},
"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"
},
"tie_word_embeddings": false,
"transformers_version": "5.20.1",
"use_cache": true,
"vocab_size": 248320
}