spuun commited on
Commit
ae1ede0
·
1 Parent(s): c2cdfae

feat: model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ adapter/* filter=lfs diff=lfs merge=lfs -text
37
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter/adapter_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bc8e90b73af8b88f4262915362a6e7be9608d321fd8e788c1dd8817fba2b37
3
+ size 1275
adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6083bf71bea3053b6c87b125e591a1e77e487f1331b1af6fae7fca47b7847bb0
3
+ size 214559840
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Mistral3ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "dtype": "float16",
7
+ "eos_token_id": 2,
8
+ "image_token_index": 10,
9
+ "model_name": "unsloth/ministral-3-8b-base-2512",
10
+ "model_type": "mistral3",
11
+ "multimodal_projector_bias": false,
12
+ "pad_token_id": 11,
13
+ "projector_hidden_act": "gelu",
14
+ "spatial_merge_size": 2,
15
+ "text_config": {
16
+ "attention_dropout": 0.0,
17
+ "bos_token_id": 1,
18
+ "dtype": "float16",
19
+ "eos_token_id": 2,
20
+ "head_dim": 128,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 4096,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 14336,
25
+ "max_position_embeddings": 262144,
26
+ "model_type": "ministral3",
27
+ "num_attention_heads": 32,
28
+ "num_hidden_layers": 34,
29
+ "num_key_value_heads": 8,
30
+ "pad_token_id": 11,
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_parameters": {
33
+ "beta_fast": 32.0,
34
+ "beta_slow": 1.0,
35
+ "factor": 16.0,
36
+ "llama_4_scaling_beta": 0.1,
37
+ "mscale": 1.0,
38
+ "mscale_all_dim": 1.0,
39
+ "original_max_position_embeddings": 16384,
40
+ "rope_theta": 1000000.0,
41
+ "rope_type": "yarn",
42
+ "type": "yarn"
43
+ },
44
+ "sliding_window": null,
45
+ "tie_word_embeddings": false,
46
+ "use_cache": true,
47
+ "vocab_size": 131072
48
+ },
49
+ "tie_word_embeddings": false,
50
+ "transformers_version": "5.5.0",
51
+ "unsloth_fixed": true,
52
+ "unsloth_version": "2026.5.5",
53
+ "vision_config": {
54
+ "attention_dropout": 0.0,
55
+ "dtype": "float16",
56
+ "head_dim": 64,
57
+ "hidden_act": "silu",
58
+ "hidden_size": 1024,
59
+ "image_size": 1540,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "model_type": "pixtral",
63
+ "num_attention_heads": 16,
64
+ "num_channels": 3,
65
+ "num_hidden_layers": 24,
66
+ "patch_size": 14,
67
+ "rope_parameters": {
68
+ "rope_theta": 10000.0,
69
+ "rope_type": "default"
70
+ }
71
+ },
72
+ "vision_feature_layer": -1
73
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 262144,
5
+ "pad_token_id": 11,
6
+ "transformers_version": "5.5.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb1ef1d39a9f1459dbc1b168f62db897618f198ef392ec3a300e2835532ecfe
3
+ size 17836126560
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
3
+ size 17078110
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "extra_special_tokens": [],
8
+ "is_local": false,
9
+ "model_max_length": 262144,
10
+ "model_specific_special_tokens": {},
11
+ "pad_token": "<pad>",
12
+ "padding_side": "left",
13
+ "processor_class": "PixtralProcessor",
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "<unk>",
16
+ "use_default_system_prompt": false
17
+ }