PKSGIN's picture
Upload folder using huggingface_hub
3ef7e25 verified
{
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 40960,
"max_window_layers": 48,
"mlp_only_layers": [],
"model_type": "qwen3_moe",
"moe_intermediate_size": 768,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 48,
"num_key_value_heads": 4,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936,
"conversion_info": {
"source_hetero_v2": "qwen3-30b-mlx-hetero-v2",
"source_q4": "qwen3-30b-mlx-q4",
"source_fp16_hf": null,
"target_format": "heterogeneous_v3",
"coding_experts": [
21,
27,
31,
43,
59,
66,
71,
113,
126
],
"coding_bits": 16,
"non_coding_bits": 4,
"description": "Hetero v3: FP16 attention/router/lm_head + FP16 coding experts + Q4 non-coding experts. mlx_lm compatible.",
"quantization_info": {
"coding_experts": {
"expert_ids": [
21,
27,
31,
43,
59,
66,
71,
113,
126
],
"bits": 16,
"format": "fp16",
"note": "User selected FP16 for code quality"
},
"non_coding_experts": {
"expert_ids": [
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20,
22,
23,
24,
25,
26,
28,
29,
30,
32,
33,
34,
35,
36,
37,
38,
39,
40,
41,
42,
44,
45,
46,
47,
48,
49,
50,
51,
52,
53,
54,
55,
56,
57,
58,
60,
61,
62,
63,
64,
65,
67,
68,
69,
70,
72,
73,
74,
75,
76,
77,
78,
79,
80,
81,
82,
83,
84,
85,
86,
87,
88,
89,
90,
91,
92,
93,
94,
95,
96,
97,
98,
99,
100,
101,
102,
103,
104,
105,
106,
107,
108,
109,
110,
111,
112,
114,
115,
116,
117,
118,
119,
120,
121,
122,
123,
124,
125,
127
],
"bits": 4,
"group_size": 64,
"format": "quantized"
},
"attention": {
"bits": 16,
"note": "User selected FP16 for better quality"
},
"router": {
"bits": 16,
"note": "User selected FP16 for accurate expert selection"
},
"lm_head": {
"bits": 16,
"note": "User selected FP16 for better token distributions"
}
}
},
"model_variant": "hetero_v3",
"_name_or_path": "qwen3-30b-mlx-hetero-v3"
}