Hugging Face's logo

aifeifei798
/
FLUX.2-klein-9B-text_encoder-8bit

Image-to-Image
Diffusion Single File
Safetensors
English
qwen3
image-generation
image-editing
flux
text_encoder
8-bit precision
bitsandbytes
Model card Files
xet
 Community
aifeifei798 commited on
Commit
a8bfae2
·
verified ·
1 Parent(s): 49418a3

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +86 -0
  2. generation_config.json +13 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12288,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "pad_token_id": null,
60
+ "quantization_config": {
61
+ "_load_in_4bit": false,
62
+ "_load_in_8bit": true,
63
+ "bnb_4bit_compute_dtype": "float32",
64
+ "bnb_4bit_quant_storage": "uint8",
65
+ "bnb_4bit_quant_type": "fp4",
66
+ "bnb_4bit_use_double_quant": false,
67
+ "llm_int8_enable_fp32_cpu_offload": false,
68
+ "llm_int8_has_fp16_weight": false,
69
+ "llm_int8_skip_modules": null,
70
+ "llm_int8_threshold": 6.0,
71
+ "load_in_4bit": false,
72
+ "load_in_8bit": true,
73
+ "quant_method": "bitsandbytes"
74
+ },
75
+ "rms_norm_eps": 1e-06,
76
+ "rope_parameters": {
77
+ "rope_theta": 1000000,
78
+ "rope_type": "default"
79
+ },
80
+ "sliding_window": null,
81
+ "tie_word_embeddings": false,
82
+ "transformers_version": "5.0.0",
83
+ "use_cache": true,
84
+ "use_sliding_window": false,
85
+ "vocab_size": 151936
86
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.0.0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ef85d96318a5d5e0e7c60fb67b333375e8a1862beed6dbfbfdc57f6b526b81
3
+ size 9441406076