CoolFace
Modelpublic

FINAL-Bench/Darwin-28B-REASON

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
52likes566downloads
config.json148 linesDownload Raw Back to root
1{
2  "architectures": [
3    "Qwen3_5ForConditionalGeneration"
4  ],
5  "bos_token_id": null,
6  "torch_dtype": "bfloat16",
7  "eos_token_id": 248046,
8  "image_token_id": 248056,
9  "language_model_only": true,
10  "model_name": "FINAL-Bench/Darwin-28B-Opus",
11  "model_type": "qwen3_5",
12  "pad_token_id": 248055,
13  "text_config": {
14    "attention_bias": false,
15    "attention_dropout": 0.0,
16    "attn_output_gate": true,
17    "bos_token_id": 248044,
18    "torch_dtype": "bfloat16",
19    "eos_token_id": 248044,
20    "full_attention_interval": 4,
21    "head_dim": 256,
22    "hidden_act": "silu",
23    "hidden_size": 5120,
24    "initializer_range": 0.02,
25    "intermediate_size": 17408,
26    "layer_types": [
27      "linear_attention",
28      "linear_attention",
29      "linear_attention",
30      "full_attention",
31      "linear_attention",
32      "linear_attention",
33      "linear_attention",
34      "full_attention",
35      "linear_attention",
36      "linear_attention",
37      "linear_attention",
38      "full_attention",
39      "linear_attention",
40      "linear_attention",
41      "linear_attention",
42      "full_attention",
43      "linear_attention",
44      "linear_attention",
45      "linear_attention",
46      "full_attention",
47      "linear_attention",
48      "linear_attention",
49      "linear_attention",
50      "full_attention",
51      "linear_attention",
52      "linear_attention",
53      "linear_attention",
54      "full_attention",
55      "linear_attention",
56      "linear_attention",
57      "linear_attention",
58      "full_attention",
59      "linear_attention",
60      "linear_attention",
61      "linear_attention",
62      "full_attention",
63      "linear_attention",
64      "linear_attention",
65      "linear_attention",
66      "full_attention",
67      "linear_attention",
68      "linear_attention",
69      "linear_attention",
70      "full_attention",
71      "linear_attention",
72      "linear_attention",
73      "linear_attention",
74      "full_attention",
75      "linear_attention",
76      "linear_attention",
77      "linear_attention",
78      "full_attention",
79      "linear_attention",
80      "linear_attention",
81      "linear_attention",
82      "full_attention",
83      "linear_attention",
84      "linear_attention",
85      "linear_attention",
86      "full_attention",
87      "linear_attention",
88      "linear_attention",
89      "linear_attention",
90      "full_attention"
91    ],
92    "linear_conv_kernel_dim": 4,
93    "linear_key_head_dim": 128,
94    "linear_num_key_heads": 16,
95    "linear_num_value_heads": 48,
96    "linear_value_head_dim": 128,
97    "mamba_ssm_dtype": "float32",
98    "max_position_embeddings": 262144,
99    "model_type": "qwen3_5_text",
100    "mtp_num_hidden_layers": 0,
101    "mtp_use_dedicated_embeddings": false,
102    "num_attention_heads": 24,
103    "num_hidden_layers": 64,
104    "num_key_value_heads": 4,
105    "output_gate_type": "swish",
106    "pad_token_id": null,
107    "partial_rotary_factor": 0.25,
108    "rms_norm_eps": 1e-06,
109    "rope_parameters": {
110      "mrope_interleaved": true,
111      "mrope_section": [
112        11,
113        11,
114        10
115      ],
116      "partial_rotary_factor": 0.25,
117      "rope_theta": 10000000,
118      "rope_type": "default"
119    },
120    "tie_word_embeddings": false,
121    "use_cache": true,
122    "vocab_size": 248320
123  },
124  "tie_word_embeddings": false,
125  "unsloth_version": "2026.4.7",
126  "use_cache": false,
127  "video_token_id": 248057,
128  "vision_config": {
129    "deepstack_visual_indexes": [],
130    "depth": 27,
131    "torch_dtype": "bfloat16",
132    "hidden_act": "gelu_pytorch_tanh",
133    "hidden_size": 1152,
134    "in_channels": 3,
135    "initializer_range": 0.02,
136    "intermediate_size": 4304,
137    "model_type": "qwen3_5",
138    "num_heads": 16,
139    "num_position_embeddings": 2304,
140    "out_hidden_size": 5120,
141    "patch_size": 16,
142    "spatial_merge_size": 2,
143    "temporal_patch_size": 2
144  },
145  "vision_end_token_id": 248054,
146  "vision_start_token_id": 248053
147}
148