Hugging Face's logo

thelamapi
/
next2.5

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
turkish
türkiye
reasoning
vision-language
vlm
multimodal
lamapi
next2.5
qwen3.5
gemma-3
text-generation
open-source
4b
edge-ai
large-language-model
llm
thinking-mode
conversational
Model card Files
xet
Community
Lamapi commited on
Commit
7b4ed1a
·
verified ·
1 Parent(s): bf3b1d7

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show
  1. README.md +1 -0
  2. config.json +115 -0
  3. generation_config.json +10 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - unsloth
7
  - qwen3_5
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - qwen3_5
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_name": "unsloth/Qwen3.5-4B",
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248055,
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": 2560,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 9216,
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
+ ],
58
+ "linear_conv_kernel_dim": 4,
59
+ "linear_key_head_dim": 128,
60
+ "linear_num_key_heads": 16,
61
+ "linear_num_value_heads": 32,
62
+ "linear_value_head_dim": 128,
63
+ "mamba_ssm_dtype": "float32",
64
+ "max_position_embeddings": 262144,
65
+ "mlp_only_layers": [],
66
+ "model_type": "qwen3_5_text",
67
+ "mtp_num_hidden_layers": 1,
68
+ "mtp_use_dedicated_embeddings": false,
69
+ "num_attention_heads": 16,
70
+ "num_hidden_layers": 32,
71
+ "num_key_value_heads": 4,
72
+ "pad_token_id": null,
73
+ "partial_rotary_factor": 0.25,
74
+ "rms_norm_eps": 1e-06,
75
+ "rope_parameters": {
76
+ "mrope_interleaved": true,
77
+ "mrope_section": [
78
+ 11,
79
+ 11,
80
+ 10
81
+ ],
82
+ "partial_rotary_factor": 0.25,
83
+ "rope_theta": 10000000,
84
+ "rope_type": "default"
85
+ },
86
+ "tie_word_embeddings": true,
87
+ "use_cache": true,
88
+ "vocab_size": 248320
89
+ },
90
+ "tie_word_embeddings": true,
91
+ "transformers_version": "5.2.0",
92
+ "unsloth_fixed": true,
93
+ "unsloth_version": "2026.3.3",
94
+ "use_cache": false,
95
+ "video_token_id": 248057,
96
+ "vision_config": {
97
+ "deepstack_visual_indexes": [],
98
+ "depth": 24,
99
+ "dtype": "bfloat16",
100
+ "hidden_act": "gelu_pytorch_tanh",
101
+ "hidden_size": 1024,
102
+ "in_channels": 3,
103
+ "initializer_range": 0.02,
104
+ "intermediate_size": 4096,
105
+ "model_type": "qwen3_5",
106
+ "num_heads": 16,
107
+ "num_position_embeddings": 2304,
108
+ "out_hidden_size": 2560,
109
+ "patch_size": 16,
110
+ "spatial_merge_size": 2,
111
+ "temporal_patch_size": 2
112
+ },
113
+ "vision_end_token_id": 248054,
114
+ "vision_start_token_id": 248053
115
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248044
6
+ ],
7
+ "pad_token_id": 248055,
8
+ "transformers_version": "5.2.0",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7485c5df9810212f244bd04fb3e25cc60e85d2074d2fd33d0fbfc5d36db61c
3
+ size 9078620536