Hugging Face's logo

MatanBT
/
mia-target-model

Text Generation
Transformers
Safetensors
gemma3_text
text-generation-inference
Model card Files
xet
Community
MatanBT commited on
Commit
a103ea9
·
verified ·
1 Parent(s): 6ecc530

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. checkpoint-25/added_tokens.json +3 -0
  3. checkpoint-25/config.json +64 -0
  4. checkpoint-25/generation_config.json +13 -0
  5. checkpoint-25/model.safetensors +3 -0
  6. checkpoint-25/optimizer.pt +3 -0
  7. checkpoint-25/rng_state.pth +3 -0
  8. checkpoint-25/scheduler.pt +3 -0
  9. checkpoint-25/special_tokens_map.json +27 -0
  10. checkpoint-25/tokenizer.json +3 -0
  11. checkpoint-25/tokenizer.model +3 -0
  12. checkpoint-25/tokenizer_config.json +0 -0
  13. checkpoint-25/trainer_state.json +48 -0
  14. checkpoint-25/training_args.bin +3 -0
  15. model.safetensors +1 -1
  16. training_args.bin +1 -1
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-25/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
checkpoint-25/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 256,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 1152,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 6912,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention"
46
+ ],
47
+ "max_position_embeddings": 32768,
48
+ "model_type": "gemma3_text",
49
+ "num_attention_heads": 4,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 1,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_local_base_freq": 10000,
56
+ "rope_scaling": null,
57
+ "rope_theta": 1000000,
58
+ "sliding_window": 512,
59
+ "sliding_window_pattern": 6,
60
+ "transformers_version": "4.57.1",
61
+ "use_bidirectional_attention": false,
62
+ "use_cache": true,
63
+ "vocab_size": 262144
64
+ }
checkpoint-25/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.57.1"
13
+ }
checkpoint-25/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff2a9ff2be33164eb4b5681f5734fbe20f2887f3df2026138fe402193e0e5489
3
+ size 1999811208
checkpoint-25/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a902402fb0bd22869f6fa90908d021dfcd6c0f1ac046ca097bfe4dc4a3956442
3
+ size 3999834207
checkpoint-25/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
checkpoint-25/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309f230498306d1e02c1edfde487e443f2140fc876ab6778c95d515e6af26091
3
+ size 1465
checkpoint-25/special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<eos>",
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
checkpoint-25/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5eba787198c9cb1d12d0dc4d653f46747749da078219b0b3f4a11b7487eb19
3
+ size 33384832
checkpoint-25/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
checkpoint-25/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-25/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 25,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 10.9375,
15
+ "learning_rate": 3.2000000000000005e-05,
16
+ "loss": 2.3059,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 5.90625,
22
+ "learning_rate": 1.2e-05,
23
+ "loss": 1.6324,
24
+ "step": 20
25
+ }
26
+ ],
27
+ "logging_steps": 10,
28
+ "max_steps": 25,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 1,
31
+ "save_steps": 500,
32
+ "stateful_callbacks": {
33
+ "TrainerControl": {
34
+ "args": {
35
+ "should_epoch_stop": false,
36
+ "should_evaluate": false,
37
+ "should_log": false,
38
+ "should_save": true,
39
+ "should_training_stop": true
40
+ },
41
+ "attributes": {}
42
+ }
43
+ },
44
+ "total_flos": 53598417715200.0,
45
+ "train_batch_size": 4,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
checkpoint-25/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42992e9dde08604df4ac24555ed19f571b093b9cf4234be37f7fb8b1b1f62d4
3
+ size 5777
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd77b0407acd333d63aab274c59ba454fa0f0b1068e79dbff8c9ad1c10bf67e4
3
  size 1999811208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff2a9ff2be33164eb4b5681f5734fbe20f2887f3df2026138fe402193e0e5489
3
  size 1999811208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e93d9f3f945e396f1877926b144cf5f736af00e039a1795a03cce837086bd9b4
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42992e9dde08604df4ac24555ed19f571b093b9cf4234be37f7fb8b1b1f62d4
3
  size 5777