Xenova HF Staff commited on
Commit
5c88f67
·
verified ·
1 Parent(s): 13508c8

Upload Qwen3_5ForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +81 -0
  2. generation_config.json +14 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "model_type": "qwen3_5",
8
+ "text_config": {
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_output_gate": true,
12
+ "bos_token_id": null,
13
+ "dtype": "bfloat16",
14
+ "eos_token_id": 248044,
15
+ "full_attention_interval": 4,
16
+ "head_dim": 32,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 8,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 32,
21
+ "layer_types": [
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention"
26
+ ],
27
+ "linear_conv_kernel_dim": 4,
28
+ "linear_key_head_dim": 32,
29
+ "linear_num_key_heads": 4,
30
+ "linear_num_value_heads": 8,
31
+ "linear_value_head_dim": 32,
32
+ "mamba_ssm_dtype": "float32",
33
+ "max_position_embeddings": 262144,
34
+ "mlp_only_layers": [],
35
+ "model_type": "qwen3_5_text",
36
+ "mtp_num_hidden_layers": 1,
37
+ "mtp_use_dedicated_embeddings": false,
38
+ "num_attention_heads": 8,
39
+ "num_hidden_layers": 4,
40
+ "num_key_value_heads": 4,
41
+ "pad_token_id": null,
42
+ "partial_rotary_factor": 0.25,
43
+ "rms_norm_eps": 1e-06,
44
+ "rope_parameters": {
45
+ "mrope_interleaved": true,
46
+ "mrope_section": [
47
+ 1,
48
+ 1,
49
+ 2
50
+ ],
51
+ "partial_rotary_factor": 0.25,
52
+ "rope_theta": 10000000,
53
+ "rope_type": "default"
54
+ },
55
+ "tie_word_embeddings": false,
56
+ "use_cache": true,
57
+ "vocab_size": 248320
58
+ },
59
+ "tie_word_embeddings": false,
60
+ "transformers_version": "5.3.0.dev0",
61
+ "video_token_id": 248057,
62
+ "vision_config": {
63
+ "deepstack_visual_indexes": [],
64
+ "depth": 2,
65
+ "dtype": "bfloat16",
66
+ "hidden_act": "gelu_pytorch_tanh",
67
+ "hidden_size": 64,
68
+ "in_channels": 3,
69
+ "initializer_range": 0.02,
70
+ "intermediate_size": 128,
71
+ "model_type": "qwen3_5",
72
+ "num_heads": 2,
73
+ "num_position_embeddings": 2304,
74
+ "out_hidden_size": 8,
75
+ "patch_size": 16,
76
+ "spatial_merge_size": 2,
77
+ "temporal_patch_size": 2
78
+ },
79
+ "vision_end_token_id": 248054,
80
+ "vision_start_token_id": 248053
81
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.3.0.dev0",
13
+ "trust_remote_code": true
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017413fd84105c745fa2c483a42c0f3a63cb63e6428480fd33b20d5969293582
3
+ size 8803200