Hugging Face's logo

simonguest
/
code-hint-onnx

ONNX
gemma3_text
Model card Files
xet
Community
simonguest commited on
Commit
d2c1b81
·
verified ·
1 Parent(s): ec4c253

Upload initial ONNX files

Browse files
Files changed (15) hide show
  1. .gitattributes +5 -0
  2. chat_template.jinja +47 -0
  3. config.json +74 -0
  4. generation_config.json +13 -0
  5. onnx/model.onnx +3 -0
  6. onnx/model.onnx_data +3 -0
  7. onnx/model_fp16.onnx +3 -0
  8. onnx/model_fp16.onnx_data +3 -0
  9. onnx/model_q4.onnx +3 -0
  10. onnx/model_q4.onnx_data +3 -0
  11. onnx/model_q4f16.onnx +3 -0
  12. onnx/model_q4f16.onnx_data +3 -0
  13. special_tokens_map.json +33 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": [
13
+ 1,
14
+ 106
15
+ ],
16
+ "final_logit_softcapping": null,
17
+ "head_dim": 256,
18
+ "hidden_activation": "gelu_pytorch_tanh",
19
+ "hidden_size": 1152,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 6912,
22
+ "layer_types": [
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "model_type": "gemma3_text",
52
+ "num_attention_heads": 4,
53
+ "num_hidden_layers": 26,
54
+ "num_key_value_heads": 1,
55
+ "pad_token_id": 0,
56
+ "query_pre_attn_scalar": 256,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_local_base_freq": 10000,
59
+ "rope_scaling": null,
60
+ "rope_theta": 1000000,
61
+ "sliding_window": 512,
62
+ "transformers_version": "4.56.1",
63
+ "use_bidirectional_attention": false,
64
+ "use_cache": true,
65
+ "vocab_size": 262144,
66
+ "transformers.js_config": {
67
+ "dtype": "fp32",
68
+ "use_external_data_format": true,
69
+ "kv_cache_dtype": {
70
+ "q4f16": "float16",
71
+ "fp16": "float16"
72
+ }
73
+ }
74
+ }
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": "4.56.1"
13
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b104e1c70f75a0c981fc12ddd5bbf481dcd117969d6c9455b92cbb0ad6743088
3
+ size 277873
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a436be7bc5fc6c0447e5a0cc7d850616392472d1f7a388aa62fc780dbf8ecf52
3
+ size 4066652672
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6948d58a0925403ac44c0bd5fad6f79c9aef82e683c513569e8dd9e9bd22ee29
3
+ size 371248
onnx/model_fp16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47fc9247a76563af0996a7a1442fe0190d5b45afbd86bcbdf7741d7fa3a5507
3
+ size 2033594880
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a68390ff60ff7a372aed8356dfb81cef5be6f1d9de50d889816fe23f7131ac8
3
+ size 344783
onnx/model_q4.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc26f9ea0d167f72f8826878bd1908175f53120007e45a93f88a06eb042db89
3
+ size 1711706624
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de5e225b26616ee79d13c5ce6117c4c686b969dda68a207457033dcc2198aa6
3
+ size 437521
onnx/model_q4f16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd8215c30bbea4ffc63df6bbc2e730bd61ab7d71e9639b7a1bac1f505d5211c
3
+ size 1030562304
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": "<eos>",
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 sha256:2498e3e627f26b464bd39d53b530af6be5b474f72e1079256038967699c422b1
3
+ size 20323106
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff