Hugging Face's logo

dddsdadf
/
mimosa_agent

Safetensors
Model card Files
xet
 Community
dddsdadf commited on
Commit
5d59b23
·
verified ·
1 Parent(s): 1551775

Upload merged_model/config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. merged_model/config.json +110 -0
merged_model/config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 25600,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
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
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention"
78
+ ],
79
+ "max_position_embeddings": 40960,
80
+ "max_window_layers": 64,
81
+ "model_type": "qwen3",
82
+ "num_attention_heads": 64,
83
+ "num_hidden_layers": 64,
84
+ "num_key_value_heads": 8,
85
+ "pad_token_id": 151654,
86
+ "quantization_config": {
87
+ "bnb_4bit_compute_dtype": "bfloat16",
88
+ "bnb_4bit_quant_type": "nf4",
89
+ "bnb_4bit_use_double_quant": true,
90
+ "llm_int8_enable_fp32_cpu_offload": false,
91
+ "llm_int8_has_fp16_weight": false,
92
+ "llm_int8_skip_modules": null,
93
+ "llm_int8_threshold": 6.0,
94
+ "load_in_4bit": true,
95
+ "load_in_8bit": false,
96
+ "quant_method": "bitsandbytes"
97
+ },
98
+ "rms_norm_eps": 1e-06,
99
+ "rope_scaling": null,
100
+ "rope_theta": 1000000,
101
+ "sliding_window": null,
102
+ "tie_word_embeddings": false,
103
+ "torch_dtype": "bfloat16",
104
+ "transformers_version": "4.53.0",
105
+ "unsloth_fixed": true,
106
+ "unsloth_version": "2025.6.12",
107
+ "use_cache": true,
108
+ "use_sliding_window": false,
109
+ "vocab_size": 151936
110
+ }