Hugging Face's logo

silx-ai
/
Quasar-10B

Text Generation
Transformers
Safetensors
English
Arabic
quasar
silx-ai
foundation-model
10b
long-context
llm
gla
linear-attention
2m-context
conversational
custom_code
Model card Files
xet
 Community
eyad-silx commited on
Commit
8b7a984
·
verified ·
1 Parent(s): de77413

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +114 -0
config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "QuasarForCausalLM"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "model_type": "quasar",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 248044,
13
+ "full_attention_interval": 4,
14
+ "head_dim": 256,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 12288,
19
+ "layer_types": [
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "full_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention"
52
+ ],
53
+ "linear_conv_kernel_dim": 4,
54
+ "linear_key_head_dim": 128,
55
+ "linear_num_key_heads": 16,
56
+ "linear_num_value_heads": 32,
57
+ "linear_value_head_dim": 128,
58
+ "max_position_embeddings": 2097152,
59
+ "mlp_only_layers": [],
60
+ "model_type": "quasar_text",
61
+ "mtp_num_hidden_layers": 1,
62
+ "mtp_use_dedicated_embeddings": false,
63
+ "num_attention_heads": 16,
64
+ "num_hidden_layers": 32,
65
+ "num_key_value_heads": 4,
66
+ "rms_norm_eps": 1e-06,
67
+ "use_cache": true,
68
+ "vocab_size": 248320,
69
+ "mamba_ssm_dtype": "float32",
70
+ "rope_parameters": {
71
+ "mrope_interleaved": true,
72
+ "mrope_section": [
73
+ 11,
74
+ 11,
75
+ 10
76
+ ],
77
+ "rope_type": "default",
78
+ "rope_theta": 10000000,
79
+ "partial_rotary_factor": 0.25
80
+ },
81
+ "use_gla": true,
82
+ "use_nope": true
83
+ },
84
+ "tie_word_embeddings": false,
85
+ "transformers_version": "4.57.0.dev0",
86
+ "video_token_id": 248057,
87
+ "vision_config": {
88
+ "deepstack_visual_indexes": [],
89
+ "depth": 27,
90
+ "hidden_act": "gelu_pytorch_tanh",
91
+ "hidden_size": 1152,
92
+ "in_channels": 3,
93
+ "initializer_range": 0.02,
94
+ "intermediate_size": 4304,
95
+ "model_type": "quasar_vision",
96
+ "num_heads": 16,
97
+ "num_position_embeddings": 2304,
98
+ "out_hidden_size": 4096,
99
+ "patch_size": 16,
100
+ "spatial_merge_size": 2,
101
+ "temporal_patch_size": 2
102
+ },
103
+ "vision_end_token_id": 248054,
104
+ "vision_start_token_id": 248053,
105
+ "use_gla": true,
106
+ "use_nope": true,
107
+ "max_position_embeddings": 2097152,
108
+ "auto_map": {
109
+ "AutoConfig": "configuration_qwen3_5.QuasarConfig",
110
+ "AutoModel": "modeling_qwen3_5.QuasarModel",
111
+ "AutoModelForCausalLM": "modeling_qwen3_5.QuasarForCausalLM"
112
+ },
113
+ "full_attention_interval": 4
114
+ }