Hugging Face's logo

guyhadad01
/
EncodeRec_300M_Toys

TensorBoard
Safetensors
gemma3_text
Model card Files
xet
Metrics Community
guyhadad01 commited on
Commit
e434d6b
·
verified ·
1 Parent(s): 9a0e7e9

Training in progress, step 200

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. config.json +61 -0
  4. model.safetensors +3 -0
  5. runs/Sep28_19-30-20_ip-172-31-44-130/events.out.tfevents.1759087822.ip-172-31-44-130 +3 -0
  6. runs/Sep28_19-32-07_ip-172-31-44-130/events.out.tfevents.1759087930.ip-172-31-44-130 +3 -0
  7. runs/Sep28_19-32-31_ip-172-31-44-130/events.out.tfevents.1759087953.ip-172-31-44-130 +3 -0
  8. runs/Sep28_19-33-11_ip-172-31-44-130/events.out.tfevents.1759087993.ip-172-31-44-130 +3 -0
  9. runs/Sep28_19-33-52_ip-172-31-44-130/events.out.tfevents.1759088033.ip-172-31-44-130 +3 -0
  10. runs/Sep28_19-34-48_ip-172-31-44-130/events.out.tfevents.1759088090.ip-172-31-44-130 +3 -0
  11. runs/Sep28_19-35-37_ip-172-31-44-130/events.out.tfevents.1759088138.ip-172-31-44-130 +3 -0
  12. runs/Sep28_19-44-56_ip-172-31-44-130/events.out.tfevents.1759088698.ip-172-31-44-130 +3 -0
  13. runs/Sep30_14-20-49_ip-172-31-44-130/events.out.tfevents.1759242051.ip-172-31-44-130 +3 -0
  14. runs/Sep30_14-22-38_ip-172-31-44-130/events.out.tfevents.1759242159.ip-172-31-44-130 +3 -0
  15. runs/Sep30_14-28-12_ip-172-31-44-130/events.out.tfevents.1759242495.ip-172-31-44-130 +3 -0
  16. runs/Sep30_14-29-58_ip-172-31-44-130/events.out.tfevents.1759242599.ip-172-31-44-130 +3 -0
  17. runs/Sep30_14-30-29_ip-172-31-44-130/events.out.tfevents.1759242630.ip-172-31-44-130 +3 -0
  18. special_tokens_map.json +33 -0
  19. tokenizer.json +3 -0
  20. tokenizer.model +3 -0
  21. tokenizer_config.json +0 -0
  22. training_args.bin +3 -0
  23. vocab.txt +0 -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
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3TextModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "dtype": "float32",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1152,
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": 2048,
45
+ "model_type": "gemma3_text",
46
+ "num_attention_heads": 3,
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_local_base_freq": 10000.0,
53
+ "rope_scaling": null,
54
+ "rope_theta": 1000000.0,
55
+ "sliding_window": 512,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.55.2",
58
+ "use_bidirectional_attention": true,
59
+ "use_cache": true,
60
+ "vocab_size": 262144
61
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3569d3e977da69f1e6effdc5cfd35f2c31712c0f88b884d222e1b60040f0e26
3
+ size 1211486072
runs/Sep28_19-30-20_ip-172-31-44-130/events.out.tfevents.1759087822.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2492cff60aff95e838131a07a3b4f4115ae8fbf264b399364ac0bf7540ee5ee3
3
+ size 4386
runs/Sep28_19-32-07_ip-172-31-44-130/events.out.tfevents.1759087930.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaccd232b128721dc0faa96a5cea7bcf6b2e46ed50cf60dbb2eefdda3f01f29a
3
+ size 4386
runs/Sep28_19-32-31_ip-172-31-44-130/events.out.tfevents.1759087953.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6710820d0c3347feb9affec28962fb888c8a3b0a3595804effcd529ddd5c19c3
3
+ size 4386
runs/Sep28_19-33-11_ip-172-31-44-130/events.out.tfevents.1759087993.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0f485d1892158cc94138e0d148d938f401eaddf0c95082ed1c36885b1cbf78
3
+ size 4386
runs/Sep28_19-33-52_ip-172-31-44-130/events.out.tfevents.1759088033.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0473dd5574ed459032e0966d543d00a2694dbb390a4747ee4b123e3765bebaf5
3
+ size 4386
runs/Sep28_19-34-48_ip-172-31-44-130/events.out.tfevents.1759088090.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c53308069fbfad592cc6e0e750430f8559a3d3089b3dbb0178243292356733
3
+ size 4385
runs/Sep28_19-35-37_ip-172-31-44-130/events.out.tfevents.1759088138.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347e4b2317df9ceaa09ff8ee6226ee3beba17279e8d5a09a5a9a254260173898
3
+ size 6702
runs/Sep28_19-44-56_ip-172-31-44-130/events.out.tfevents.1759088698.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb9ea2a5427633abf4d17dd996d4522791ea449d7290379ad9ec08e2bd00893
3
+ size 9167
runs/Sep30_14-20-49_ip-172-31-44-130/events.out.tfevents.1759242051.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95999135298aecd673c595aac0cb8a1abc260e1030e158c670f72bca0047e4c
3
+ size 4481
runs/Sep30_14-22-38_ip-172-31-44-130/events.out.tfevents.1759242159.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbc47c3bd41d48a3c8b140e082e40615c435bddd0217df0e354f7f324faf9b2
3
+ size 4485
runs/Sep30_14-28-12_ip-172-31-44-130/events.out.tfevents.1759242495.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a85b205f0faecd660df5762a384fa678d67af0ddc1e7e4f2a5abd64f377f7f
3
+ size 4418
runs/Sep30_14-29-58_ip-172-31-44-130/events.out.tfevents.1759242599.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a3be7e79d1bba1787913df75c09566151e1a8fa30324ac188652137170dc60
3
+ size 4418
runs/Sep30_14-30-29_ip-172-31-44-130/events.out.tfevents.1759242630.ip-172-31-44-130 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac13bceae3bfe71b8c09c4f4897dc50a25e68bd11b199a2343a86171925a009
3
+ size 5258
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:c79a190be01275b078b3574d02188abc5784e5651a101b20d826371ba8e897dc
3
+ size 33385261
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08e873fcc6af5914cd3b33b8457f079faba879550636b5ef8bf74269ab02c7c
3
+ size 6161
vocab.txt ADDED
The diff for this file is too large to render. See raw diff