Hugging Face's logo

3CPO-models
/
nietsvermoedend-equal-4b

Safetensors
gemma3_text
Model card Files
xet
 Community
jjzha commited on
Commit
3eb81a8
·
verified ·
1 Parent(s): f1f8be4

Update main to iter_0005500

Browse files
Files changed (12) hide show
  1. .gitattributes +4 -0
  2. .ipynb_checkpoints/equal.large-checkpoint.json +3 -0
  3. .ipynb_checkpoints/tokenizer-checkpoint.json +3 -0
  4. .ipynb_checkpoints/tokenizer_config-checkpoint.json +10 -0
  5. added_tokens.json +3 -0
  6. config.json +72 -0
  7. equal.large.json +3 -0
  8. generation_config.json +14 -0
  9. model.safetensors +3 -0
  10. special_tokens_map.json +33 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +10 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ .ipynb_checkpoints/equal.large-checkpoint.json filter=lfs diff=lfs merge=lfs -text
37
+ .ipynb_checkpoints/tokenizer-checkpoint.json filter=lfs diff=lfs merge=lfs -text
38
+ equal.large.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/equal.large-checkpoint.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f47c0aa606d2fb73c16c6471d209a2bcf9713723a8cfaa651a846b79937366
3
+ size 20116262
.ipynb_checkpoints/tokenizer-checkpoint.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39fa64f2efb0940ddf768abbbf7a9212a9f19bea6021f313e62321e3c97fff96
3
+ size 20116826
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "eos_token": "<eos>",
5
+ "mask_token": "<mask>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "GemmaTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token_id": 1,
11
+ "final_logit_softcapping": null,
12
+ "head_dim": 256,
13
+ "hidden_activation": "gelu_pytorch_tanh",
14
+ "hidden_size": 2560,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 10240,
17
+ "layer_types": [
18
+ "sliding_attention",
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention"
52
+ ],
53
+ "max_position_embeddings": 131072,
54
+ "model_type": "gemma3_text",
55
+ "num_attention_heads": 16,
56
+ "num_hidden_layers": 34,
57
+ "num_key_value_heads": 4,
58
+ "pad_token_id": 0,
59
+ "query_pre_attn_scalar": 256,
60
+ "rms_norm_eps": 1e-06,
61
+ "rope_local_base_freq": 10000.0,
62
+ "rope_scaling": {
63
+ "factor": 8.0,
64
+ "rope_type": "linear"
65
+ },
66
+ "rope_theta": 1000000.0,
67
+ "sliding_window": 1024,
68
+ "transformers_version": "4.57.3",
69
+ "use_bidirectional_attention": false,
70
+ "use_cache": true,
71
+ "vocab_size": 256000
72
+ }
equal.large.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f47c0aa606d2fb73c16c6471d209a2bcf9713723a8cfaa651a846b79937366
3
+ size 20116262
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3",
13
+ "trust_remote_code": false
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8d07a181171ddf9ba0ce1fb2dc83768584f7ec5926b7814eef49bb56d05923
3
+ size 8441824808
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30793f266543cd184916db4ff31318c06ae35c764dd61ed4f5304ba106d24ecb
3
+ size 20116930
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "eos_token": "<eos>",
5
+ "mask_token": "<mask>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "GemmaTokenizer",
9
+ "unk_token": "<unk>"
10
+ }