Hugging Face's logo

guyhadad01
/
EncodeRec_300M_Beauty

TensorBoard
Safetensors
gemma3_text
Model card Files
xet
Metrics Community
guyhadad01 commited on
Commit
de28f07
·
verified ·
1 Parent(s): 2b712ea

Training in progress, step 200

Browse files
Files changed (24) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. chat_template.jinja +85 -0
  4. config.json +60 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. runs/Oct10_09-14-23_ip-172-31-44-130/events.out.tfevents.1760087665.ip-172-31-44-130.129292.0 +3 -0
  8. runs/Oct13_11-31-30_ip-172-31-44-130/events.out.tfevents.1760355092.ip-172-31-44-130.64297.0 +3 -0
  9. runs/Oct13_11-32-27_ip-172-31-44-130/events.out.tfevents.1760355148.ip-172-31-44-130.75867.0 +3 -0
  10. runs/Oct13_11-35-30_ip-172-31-44-130/events.out.tfevents.1760355331.ip-172-31-44-130.76888.0 +3 -0
  11. runs/Oct15_07-27-48_ip-172-31-44-130/events.out.tfevents.1760513270.ip-172-31-44-130.39696.0 +3 -0
  12. runs/Oct15_07-28-13_ip-172-31-44-130/events.out.tfevents.1760513294.ip-172-31-44-130.39696.1 +3 -0
  13. runs/Oct15_07-56-55_ip-172-31-44-130/events.out.tfevents.1760515017.ip-172-31-44-130.77663.0 +3 -0
  14. runs/Oct15_07-59-24_ip-172-31-44-130/events.out.tfevents.1760515166.ip-172-31-44-130.77663.1 +3 -0
  15. runs/Oct24_08-23-31_ip-172-31-44-130/events.out.tfevents.1761294212.ip-172-31-44-130.20083.0 +3 -0
  16. runs/Oct24_09-31-35_ip-172-31-44-130/events.out.tfevents.1761298297.ip-172-31-44-130.94906.0 +3 -0
  17. runs/Oct24_09-34-08_ip-172-31-44-130/events.out.tfevents.1761298449.ip-172-31-44-130.96236.0 +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.json +0 -0
  24. 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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
27
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- set reasoning_content = '' %}
31
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
32
+ {%- set reasoning_content = message.reasoning_content %}
33
+ {%- else %}
34
+ {%- if '</think>' in message.content %}
35
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
36
+ {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
37
+ {%- endif %}
38
+ {%- endif %}
39
+ {%- if loop.index0 > ns.last_query_index %}
40
+ {%- if loop.last or (not loop.last and reasoning_content) %}
41
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
42
+ {%- else %}
43
+ {{- '<|im_start|>' + message.role + '\n' + content }}
44
+ {%- endif %}
45
+ {%- else %}
46
+ {{- '<|im_start|>' + message.role + '\n' + content }}
47
+ {%- endif %}
48
+ {%- if message.tool_calls %}
49
+ {%- for tool_call in message.tool_calls %}
50
+ {%- if (loop.first and content) or (not loop.first) %}
51
+ {{- '\n' }}
52
+ {%- endif %}
53
+ {%- if tool_call.function %}
54
+ {%- set tool_call = tool_call.function %}
55
+ {%- endif %}
56
+ {{- '<tool_call>\n{"name": "' }}
57
+ {{- tool_call.name }}
58
+ {{- '", "arguments": ' }}
59
+ {%- if tool_call.arguments is string %}
60
+ {{- tool_call.arguments }}
61
+ {%- else %}
62
+ {{- tool_call.arguments | tojson }}
63
+ {%- endif %}
64
+ {{- '}\n</tool_call>' }}
65
+ {%- endfor %}
66
+ {%- endif %}
67
+ {{- '<|im_end|>\n' }}
68
+ {%- elif message.role == "tool" %}
69
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
70
+ {{- '<|im_start|>user' }}
71
+ {%- endif %}
72
+ {{- '\n<tool_response>\n' }}
73
+ {{- message.content }}
74
+ {{- '\n</tool_response>' }}
75
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
76
+ {{- '<|im_end|>\n' }}
77
+ {%- endif %}
78
+ {%- endif %}
79
+ {%- endfor %}
80
+ {%- if add_generation_prompt %}
81
+ {{- '<|im_start|>assistant\n' }}
82
+ {%- if enable_thinking is defined and enable_thinking is false %}
83
+ {{- '<think>\n\n</think>\n\n' }}
84
+ {%- endif %}
85
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "bfloat16",
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": 257,
56
+ "transformers_version": "4.57.0",
57
+ "use_bidirectional_attention": true,
58
+ "use_cache": true,
59
+ "vocab_size": 262144
60
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00293b8b4761f0d06286339bd7a4cc183edee2c660dc984093785075d782b637
3
+ size 605759848
runs/Oct10_09-14-23_ip-172-31-44-130/events.out.tfevents.1760087665.ip-172-31-44-130.129292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e7289d1981b4d81496fff2acf2caaa259d77ccda3376b0046f03e10d7a54e2
3
+ size 4511
runs/Oct13_11-31-30_ip-172-31-44-130/events.out.tfevents.1760355092.ip-172-31-44-130.64297.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79df46a5850d5049016b37e7a805a17189d2a1e5bc466328920d8217676a1b63
3
+ size 4603
runs/Oct13_11-32-27_ip-172-31-44-130/events.out.tfevents.1760355148.ip-172-31-44-130.75867.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9a14fbd825017023d9de9fc7ffc335785f7992b758c7b64ca3c99b2e71ab71
3
+ size 4603
runs/Oct13_11-35-30_ip-172-31-44-130/events.out.tfevents.1760355331.ip-172-31-44-130.76888.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a1eef828ac3ca727a8ac33ca98fbd2770569c20a5a5059a4444005ea700660d
3
+ size 4951
runs/Oct15_07-27-48_ip-172-31-44-130/events.out.tfevents.1760513270.ip-172-31-44-130.39696.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd43b55c9534f7f2c6088a2aef0de9d2e714d8afbb66767693cfaf1d7c25827
3
+ size 4512
runs/Oct15_07-28-13_ip-172-31-44-130/events.out.tfevents.1760513294.ip-172-31-44-130.39696.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c8b5783d66622a961867d06999da5baf179cbe8260c983c3fe9b8b8eb873a6
3
+ size 9078
runs/Oct15_07-56-55_ip-172-31-44-130/events.out.tfevents.1760515017.ip-172-31-44-130.77663.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6072e10a753df9f6d63a9e87be3fec20080fad056c0d21eb9ebb5dd691a928
3
+ size 4513
runs/Oct15_07-59-24_ip-172-31-44-130/events.out.tfevents.1760515166.ip-172-31-44-130.77663.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e698f0c42de97e5cc47cff40a7b9df8e9b66340fbeee4f07f4525f5c1eba97b
3
+ size 4513
runs/Oct24_08-23-31_ip-172-31-44-130/events.out.tfevents.1761294212.ip-172-31-44-130.20083.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95bc0b34de147cc9a62ba7fd979c4ec3893a4d955e2008ac8747158de157fab
3
+ size 4513
runs/Oct24_09-31-35_ip-172-31-44-130/events.out.tfevents.1761298297.ip-172-31-44-130.94906.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0446d9e18c0e32e859b31a25cb7e606a47561c339afa7e6b15c79bb28307cf0e
3
+ size 4606
runs/Oct24_09-34-08_ip-172-31-44-130/events.out.tfevents.1761298449.ip-172-31-44-130.96236.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a550e74f6ac897f652f51c9b2ade6c540cf19491f77913970c6f7d01e89890
3
+ size 5442
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 sha256:6468685d270b281475a8de797422da740ad1a8afa73bff9ef93badd261914b2f
3
+ size 6289
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff