hf-transformers-bot commited on
Commit
818652f
·
verified ·
1 Parent(s): 97fd27f

Update tiny models for Ministral3Model

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +39 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +24 -0
  5. tekken.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tekken.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Ministral3Model"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "head_dim": 16,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 32,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 32,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "ministral3",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "num_key_value_heads": 2,
19
+ "pad_token_id": 0,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_parameters": {
22
+ "beta_fast": 32.0,
23
+ "beta_slow": 1.0,
24
+ "factor": 16.0,
25
+ "llama_4_scaling_beta": 0.1,
26
+ "max_position_embeddings": 512,
27
+ "mscale": 1.0,
28
+ "mscale_all_dim": 1.0,
29
+ "original_max_position_embeddings": 16384,
30
+ "rope_theta": 1000000.0,
31
+ "rope_type": "yarn",
32
+ "type": "yarn"
33
+ },
34
+ "sliding_window": null,
35
+ "tie_word_embeddings": false,
36
+ "transformers_version": "5.16.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 99
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3fcbf71fdeb18a010505ef262f3082b535fc65ddba33b673818c83d16100fe0
3
+ size 72560
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_format": "channels_first",
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "PixtralImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "patch_size": 14,
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "longest_edge": 1540
23
+ }
24
+ }
tekken.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e29d19ea32eb7e26e6c0572d57cb7f9eca0f4420e0e0fe6ae1cf3be94da1c0d6
3
+ size 16753777