Ba2han commited on
Commit
878dc1c
·
verified ·
1 Parent(s): f7fa708

Upload config(7).json

Browse files
Files changed (1) hide show
  1. config(7).json +67 -0
config(7).json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Mistral3ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "torch_dtype": "bfloat16",
7
+ "eos_token_id": 2,
8
+ "image_token_index": 10,
9
+ "model_type": "mistral3",
10
+ "multimodal_projector_bias": false,
11
+ "pad_token_id": 11,
12
+ "projector_hidden_act": "gelu",
13
+ "spatial_merge_size": 2,
14
+ "text_config": {
15
+ "attention_dropout": 0.0,
16
+ "torch_dtype": "bfloat16",
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 4096,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 14336,
22
+ "max_position_embeddings": 262144,
23
+ "model_type": "ministral3",
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 34,
26
+ "num_key_value_heads": 8,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_parameters": {
29
+ "beta_fast": 32.0,
30
+ "beta_slow": 1.0,
31
+ "factor": 16.0,
32
+ "llama_4_scaling_beta": 0.1,
33
+ "mscale": 1.0,
34
+ "mscale_all_dim": 1.0,
35
+ "original_max_position_embeddings": 16384,
36
+ "rope_theta": 1000000.0,
37
+ "rope_type": "yarn",
38
+ "type": "yarn"
39
+ },
40
+ "sliding_window": null,
41
+ "use_cache": true,
42
+ "vocab_size": 131072
43
+ },
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "5.0.0.dev0",
46
+ "unsloth_fixed": true,
47
+ "vision_config": {
48
+ "attention_dropout": 0.0,
49
+ "torch_dtype": "bfloat16",
50
+ "head_dim": 64,
51
+ "hidden_act": "silu",
52
+ "hidden_size": 1024,
53
+ "image_size": 1540,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 4096,
56
+ "model_type": "pixtral",
57
+ "num_attention_heads": 16,
58
+ "num_channels": 3,
59
+ "num_hidden_layers": 24,
60
+ "patch_size": 14,
61
+ "rope_parameters": {
62
+ "rope_theta": 10000.0,
63
+ "rope_type": "default"
64
+ }
65
+ },
66
+ "vision_feature_layer": -1
67
+ }