Hugging Face's logo

sahilchachra
/
KAT-Coder-V2.5-Dev-NVFP4A16

Text Generation
Safetensors
English
qwen3_5_moe
nvfp4
fp4
nvfp4a16
compressed-tensors
llm-compressor
conversational
8-bit precision
Model card Files
xet
 Community
sahilchachra commited on
Commit
e1f5189
·
verified ·
1 Parent(s): af54f28

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +163 -0
config.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5_moe",
7
+ "quantization_config": {
8
+ "config_groups": {
9
+ "config_group_0": {
10
+ "format": "nvfp4-pack-quantized",
11
+ "input_activations": null,
12
+ "output_activations": null,
13
+ "targets": [
14
+ "Linear"
15
+ ],
16
+ "weights": {
17
+ "actorder": null,
18
+ "block_structure": null,
19
+ "dynamic": false,
20
+ "group_size": 16,
21
+ "num_bits": 4,
22
+ "observer": "memoryless_minmax",
23
+ "observer_kwargs": {},
24
+ "scale_dtype": "torch.float8_e4m3fn",
25
+ "strategy": "tensor_group",
26
+ "symmetric": true,
27
+ "type": "float",
28
+ "zp_dtype": null
29
+ }
30
+ }
31
+ },
32
+ "format": "nvfp4-pack-quantized",
33
+ "global_compression_ratio": null,
34
+ "ignore": [
35
+ "lm_head",
36
+ "re:.*embed_tokens.*",
37
+ "re:.*norm.*",
38
+ "re:.*\\.linear_attn\\..*",
39
+ "re:.*visual.*",
40
+ "re:.*\\.mtp\\..*",
41
+ "re:^mtp\\..*",
42
+ "re:.*mlp\\.gate$",
43
+ "re:.*shared_expert_gate.*"
44
+ ],
45
+ "kv_cache_scheme": null,
46
+ "quant_method": "compressed-tensors",
47
+ "quantization_status": "compressed",
48
+ "transform_config": {},
49
+ "version": "0.17.1"
50
+ },
51
+ "text_config": {
52
+ "attention_bias": false,
53
+ "attention_dropout": 0.0,
54
+ "attn_output_gate": true,
55
+ "bos_token_id": 248044,
56
+ "dtype": "bfloat16",
57
+ "eos_token_id": 248044,
58
+ "full_attention_interval": 4,
59
+ "head_dim": 256,
60
+ "hidden_act": "silu",
61
+ "hidden_size": 2048,
62
+ "initializer_range": 0.02,
63
+ "layer_types": [
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "full_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "full_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "full_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "full_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "full_attention",
88
+ "linear_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "full_attention",
92
+ "linear_attention",
93
+ "linear_attention",
94
+ "linear_attention",
95
+ "full_attention",
96
+ "linear_attention",
97
+ "linear_attention",
98
+ "linear_attention",
99
+ "full_attention",
100
+ "linear_attention",
101
+ "linear_attention",
102
+ "linear_attention",
103
+ "full_attention"
104
+ ],
105
+ "linear_conv_kernel_dim": 4,
106
+ "linear_key_head_dim": 128,
107
+ "linear_num_key_heads": 16,
108
+ "linear_num_value_heads": 32,
109
+ "linear_value_head_dim": 128,
110
+ "mamba_ssm_dtype": "float32",
111
+ "max_position_embeddings": 262144,
112
+ "model_type": "qwen3_5_moe_text",
113
+ "moe_intermediate_size": 512,
114
+ "mtp_num_hidden_layers": 0,
115
+ "mtp_use_dedicated_embeddings": false,
116
+ "num_attention_heads": 16,
117
+ "num_experts": 256,
118
+ "num_experts_per_tok": 8,
119
+ "num_hidden_layers": 40,
120
+ "num_key_value_heads": 2,
121
+ "output_router_logits": false,
122
+ "pad_token_id": null,
123
+ "partial_rotary_factor": 0.25,
124
+ "rms_norm_eps": 1e-06,
125
+ "rope_parameters": {
126
+ "mrope_interleaved": true,
127
+ "mrope_section": [
128
+ 11,
129
+ 11,
130
+ 10
131
+ ],
132
+ "partial_rotary_factor": 0.25,
133
+ "rope_theta": 10000000,
134
+ "rope_type": "default"
135
+ },
136
+ "router_aux_loss_coef": 0.001,
137
+ "shared_expert_intermediate_size": 512,
138
+ "tie_word_embeddings": false,
139
+ "use_cache": true,
140
+ "vocab_size": 248320
141
+ },
142
+ "tie_word_embeddings": false,
143
+ "transformers_version": "4.57.1",
144
+ "video_token_id": 248057,
145
+ "vision_config": {
146
+ "deepstack_visual_indexes": [],
147
+ "depth": 27,
148
+ "hidden_act": "gelu_pytorch_tanh",
149
+ "hidden_size": 1152,
150
+ "in_channels": 3,
151
+ "initializer_range": 0.02,
152
+ "intermediate_size": 4304,
153
+ "model_type": "qwen3_5_moe",
154
+ "num_heads": 16,
155
+ "num_position_embeddings": 2304,
156
+ "out_hidden_size": 2048,
157
+ "patch_size": 16,
158
+ "spatial_merge_size": 2,
159
+ "temporal_patch_size": 2
160
+ },
161
+ "vision_end_token_id": 248054,
162
+ "vision_start_token_id": 248053
163
+ }