Hugging Face's logo

khtsly
/
luau-coder-preview

Image-Text-to-Text
Transformers
Safetensors
English
qwen3_5
text-generation-inference
unsloth
conversational
Model card Files
xet
 Community
khtsly commited on
Commit
d3d1c60
·
verified ·
1 Parent(s): 4344a5f

(Trained with Unsloth)

Browse files
Files changed (2) hide show
  1. config.json +125 -125
  2. tokenizer_config.json +1 -1
config.json CHANGED
@@ -1,129 +1,129 @@
1
  {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
5
- "dtype": "bfloat16",
6
- "eos_token_id": 248046,
7
- "image_token_id": 248056,
8
- "model_name": "luau-coder-preview",
9
- "model_type": "qwen3_5",
10
- "pad_token_id": 248044,
11
- "text_config": {
12
- "attention_bias": false,
13
- "attention_dropout": 0.0,
14
- "attn_output_gate": true,
15
- "bos_token_id": null,
16
- "dtype": "bfloat16",
17
- "eos_token_id": 248044,
18
- "full_attention_interval": 4,
19
- "head_dim": 256,
20
- "hidden_act": "silu",
21
- "hidden_size": 4096,
22
- "initializer_range": 0.02,
23
- "intermediate_size": 12288,
24
- "layer_types": [
25
- "linear_attention",
26
- "linear_attention",
27
- "linear_attention",
28
- "full_attention",
29
- "linear_attention",
30
- "linear_attention",
31
- "linear_attention",
32
- "full_attention",
33
- "linear_attention",
34
- "linear_attention",
35
- "linear_attention",
36
- "full_attention",
37
- "linear_attention",
38
- "linear_attention",
39
- "linear_attention",
40
- "full_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "linear_attention",
44
- "full_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "linear_attention",
48
- "full_attention",
49
- "linear_attention",
50
- "linear_attention",
51
- "linear_attention",
52
- "full_attention",
53
- "linear_attention",
54
- "linear_attention",
55
- "linear_attention",
56
- "full_attention",
57
- "linear_attention",
58
- "linear_attention",
59
- "linear_attention",
60
- "full_attention",
61
- "linear_attention",
62
- "linear_attention",
63
- "linear_attention",
64
- "full_attention",
65
- "linear_attention",
66
- "linear_attention",
67
- "linear_attention",
68
- "full_attention",
69
- "linear_attention",
70
- "linear_attention",
71
- "linear_attention",
72
- "full_attention"
73
  ],
74
- "linear_conv_kernel_dim": 4,
75
- "linear_key_head_dim": 128,
76
- "linear_num_key_heads": 16,
77
- "linear_num_value_heads": 32,
78
- "linear_value_head_dim": 128,
79
- "mamba_ssm_dtype": "float32",
80
- "max_position_embeddings": 262144,
81
- "mlp_only_layers": [],
82
- "model_type": "qwen3_5_text",
83
- "mtp_num_hidden_layers": 1,
84
- "mtp_use_dedicated_embeddings": false,
85
- "num_attention_heads": 16,
86
- "num_hidden_layers": 48,
87
- "num_key_value_heads": 4,
88
- "pad_token_id": null,
89
- "partial_rotary_factor": 0.25,
90
- "rms_norm_eps": 1e-06,
91
- "rope_parameters": {
92
- "mrope_interleaved": true,
93
- "mrope_section": [
94
- 11,
95
- 11,
96
- 10
97
- ],
98
- "partial_rotary_factor": 0.25,
99
- "rope_theta": 10000000,
100
- "rope_type": "default"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  },
102
  "tie_word_embeddings": false,
103
- "use_cache": true,
104
- "vocab_size": 248320
105
- },
106
- "tie_word_embeddings": false,
107
- "transformers_version": "5.5.0",
108
- "unsloth_version": "2026.4.2",
109
- "video_token_id": 248057,
110
- "vision_config": {
111
- "deepstack_visual_indexes": [],
112
- "depth": 27,
113
- "dtype": "bfloat16",
114
- "hidden_act": "gelu_pytorch_tanh",
115
- "hidden_size": 1152,
116
- "in_channels": 3,
117
- "initializer_range": 0.02,
118
- "intermediate_size": 4304,
119
- "model_type": "qwen3_5",
120
- "num_heads": 16,
121
- "num_position_embeddings": 2304,
122
- "out_hidden_size": 4096,
123
- "patch_size": 16,
124
- "spatial_merge_size": 2,
125
- "temporal_patch_size": 2
126
- },
127
- "vision_end_token_id": 248054,
128
- "vision_start_token_id": 248053
129
- }
 
1
  {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
+ "torch_dtype": "bfloat16",
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_name": "luau-coder-preview",
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248044,
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "attn_output_gate": true,
15
+ "bos_token_id": null,
16
+ "torch_dtype": "bfloat16",
17
+ "eos_token_id": 248044,
18
+ "full_attention_interval": 4,
19
+ "head_dim": 256,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 4096,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 12288,
24
+ "layer_types": [
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "full_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "full_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "full_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "full_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "full_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "full_attention"
73
+ ],
74
+ "linear_conv_kernel_dim": 4,
75
+ "linear_key_head_dim": 128,
76
+ "linear_num_key_heads": 16,
77
+ "linear_num_value_heads": 32,
78
+ "linear_value_head_dim": 128,
79
+ "mamba_ssm_dtype": "float32",
80
+ "max_position_embeddings": 262144,
81
+ "mlp_only_layers": [],
82
+ "model_type": "qwen3_5_text",
83
+ "mtp_num_hidden_layers": 1,
84
+ "mtp_use_dedicated_embeddings": false,
85
+ "num_attention_heads": 16,
86
+ "num_hidden_layers": 48,
87
+ "num_key_value_heads": 4,
88
+ "pad_token_id": null,
89
+ "partial_rotary_factor": 0.25,
90
+ "rms_norm_eps": 1e-06,
91
+ "rope_parameters": {
92
+ "mrope_interleaved": true,
93
+ "mrope_section": [
94
+ 11,
95
+ 11,
96
+ 10
97
+ ],
98
+ "partial_rotary_factor": 0.25,
99
+ "rope_theta": 10000000,
100
+ "rope_type": "default"
101
+ },
102
+ "tie_word_embeddings": false,
103
+ "use_cache": true,
104
+ "vocab_size": 248320
105
  },
106
  "tie_word_embeddings": false,
107
+ "unsloth_version": "2026.4.2",
108
+ "use_cache": false,
109
+ "video_token_id": 248057,
110
+ "vision_config": {
111
+ "deepstack_visual_indexes": [],
112
+ "depth": 27,
113
+ "torch_dtype": "bfloat16",
114
+ "hidden_act": "gelu_pytorch_tanh",
115
+ "hidden_size": 1152,
116
+ "in_channels": 3,
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 4304,
119
+ "model_type": "qwen3_5",
120
+ "num_heads": 16,
121
+ "num_position_embeddings": 2304,
122
+ "out_hidden_size": 4096,
123
+ "patch_size": 16,
124
+ "spatial_merge_size": 2,
125
+ "temporal_patch_size": 2
126
+ },
127
+ "vision_end_token_id": 248054,
128
+ "vision_start_token_id": 248053
129
+ }
 
 
 
 
tokenizer_config.json CHANGED
@@ -9,7 +9,7 @@
9
  "eos_token": "<|im_end|>",
10
  "errors": "replace",
11
  "image_token": "<|image_pad|>",
12
- "is_local": false,
13
  "model_max_length": 262144,
14
  "model_specific_special_tokens": {
15
  "audio_bos_token": "<|audio_start|>",
 
9
  "eos_token": "<|im_end|>",
10
  "errors": "replace",
11
  "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
  "model_max_length": 262144,
14
  "model_specific_special_tokens": {
15
  "audio_bos_token": "<|audio_start|>",