Hugging Face's logo

logic65
/
whittle-dev

Safetensors
GGUF
whittle
research
training-checkpoints
conversational
Model card Files
xet
 Community
whittle-dev
File size: 2,791 Bytes
dfb9cc3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
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
113
114
{
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_output_gate": true,
  "bos_token_id": 248044,
  "dtype": "bfloat16",
  "eos_token_id": 248044,
  "full_attention_interval": 4,
  "head_dim": 256,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "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_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,
  "model_type": "qwen4_exp_text",
  "moe_intermediate_size": 512,
  "mtp_num_hidden_layers": 1,
  "mtp_use_dedicated_embeddings": false,
  "num_attention_heads": 16,
  "num_experts": 180,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 40,
  "num_key_value_heads": 2,
  "output_router_logits": false,
  "pad_token_id": null,
  "partial_rotary_factor": 0.25,
  "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"
  },
  "router_aux_loss_coef": 0.001,
  "shared_expert_intermediate_size": 512,
  "tie_word_embeddings": false,
  "use_cache": true,
  "vocab_size": 248320,
  "architectures": [
    "Qwen4ExpForCausalLM"
  ],
  "transformers_version": "4.57.1",
  "hc_count": 4,
  "hc_lowrank": 320,
  "indexer_n_heads": 4,
  "indexer_head_dim": 128,
  "indexer_budget": 262144,
  "indexer_compress_ratio": 4,
  "indexer_kv_heads": 1,
  "output_gate_type": "sigmoid",
  "ple_layer_ids": [
    2
  ],
  "ngram_size": 3,
  "heads_per_ngram": 4,
  "ple_conv_kernel_size": 4,
  "split_ngram_parts": 5,
  "ple_embed_dim": 2048,
  "num_embeddings_per_layer_input": 256,
  "make_ngram_vocab_size_divisible_by": 128,
  "ngram_vocab_size_base": 4880000
}