Simple00 commited on
Commit
f1ea86a
·
verified ·
1 Parent(s): 3ed4a2c

Challenger from dt06

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +69 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +3 -0
  5. tokenizer_config.json +25 -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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "dtype": "bfloat16",
11
+ "eos_token_id": 106,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 1152,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 6400,
18
+ "layer_types": [
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention"
43
+ ],
44
+ "max_position_embeddings": 32768,
45
+ "model_type": "gemma3_text",
46
+ "num_attention_heads": 4,
47
+ "num_hidden_layers": 24,
48
+ "num_key_value_heads": 1,
49
+ "pad_token_id": 0,
50
+ "query_pre_attn_scalar": 256,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_parameters": {
53
+ "full_attention": {
54
+ "rope_theta": 1000000.0,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_attention": {
58
+ "rope_theta": 10000.0,
59
+ "rope_type": "default"
60
+ }
61
+ },
62
+ "sliding_window": 512,
63
+ "sliding_window_pattern": 6,
64
+ "tie_word_embeddings": true,
65
+ "transformers_version": "5.5.4",
66
+ "use_bidirectional_attention": false,
67
+ "use_cache": false,
68
+ "vocab_size": 262144
69
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b56cd02892deb4f4e33fd00001a6f864371d5b72642d4b2df194c5e5e7b5bf
3
+ size 1807505032
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
3
+ size 33384567
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "boi_token": "<start_of_image>",
4
+ "bos_token": "<bos>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eoi_token": "<end_of_image>",
7
+ "eos_token": "<end_of_turn>",
8
+ "image_token": "<image_soft_token>",
9
+ "is_local": false,
10
+ "mask_token": "<mask>",
11
+ "model_max_length": 32768,
12
+ "model_specific_special_tokens": {
13
+ "boi_token": "<start_of_image>",
14
+ "eoi_token": "<end_of_image>",
15
+ "image_token": "<image_soft_token>"
16
+ },
17
+ "pad_token": "<pad>",
18
+ "padding_side": "left",
19
+ "processor_class": "Gemma3Processor",
20
+ "sp_model_kwargs": null,
21
+ "spaces_between_special_tokens": false,
22
+ "tokenizer_class": "GemmaTokenizer",
23
+ "unk_token": "<unk>",
24
+ "use_default_system_prompt": false
25
+ }