Hugging Face's logo

willopcbeta
/
translategemma-4b-it-Text-ONNX

Text Generation
Transformers.js
ONNX
multilingual
gemma3_text
gemma3
translation
no-vision
causal-lm
conversational
Model card Files
xet
Community
5
willopcbeta commited on
Commit
a262eff
·
verified ·
1 Parent(s): 7d0eaa6

Modifying "kv_cache_dtype" now conforms to Q4/Q4f16. The original model's dtype is now "float16".

Browse files

Fixed a bug in Q4 that caused issues with the dialogue.
OrtRun(). ERROR_CODE: 2, ERROR_MESSAGE: Unexpected input data type. Actual: (tensor(float)) , expected: (tensor(float16))

Files changed (1) hide show
  1. config.json +86 -88
config.json CHANGED
@@ -1,88 +1,86 @@
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
- "dtype": "float16",
11
- "eos_token_id": 1,
12
- "final_logit_softcapping": null,
13
- "head_dim": 256,
14
- "hidden_activation": "gelu_pytorch_tanh",
15
- "hidden_size": 2560,
16
- "initializer_range": 0.02,
17
- "intermediate_size": 10240,
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
- "sliding_attention",
44
- "sliding_attention",
45
- "sliding_attention",
46
- "sliding_attention",
47
- "sliding_attention",
48
- "full_attention",
49
- "sliding_attention",
50
- "sliding_attention",
51
- "sliding_attention",
52
- "sliding_attention"
53
- ],
54
- "max_position_embeddings": 131072,
55
- "model_type": "gemma3_text",
56
- "num_attention_heads": 8,
57
- "num_hidden_layers": 34,
58
- "num_key_value_heads": 4,
59
- "pad_token_id": 0,
60
- "query_pre_attn_scalar": 256,
61
- "rms_norm_eps": 1e-06,
62
- "rope_local_base_freq": 10000,
63
- "rope_parameters": {
64
- "full_attention": {
65
- "factor": 8.0,
66
- "rope_type": "linear"
67
- },
68
- "sliding_attention": {
69
- "rope_type": "default"
70
- }
71
- },
72
- "rope_scaling": null,
73
- "rope_theta": 1000000,
74
- "sliding_window": 1024,
75
- "transformers_version": "4.57.3",
76
- "use_bidirectional_attention": false,
77
- "use_cache": true,
78
- "vocab_size": 262208,
79
- "transformers.js_config": {
80
- "kv_cache_dtype": {
81
- "q4f16": "float16"
82
- },
83
- "use_external_data_format": {
84
- "model_q4.onnx": 3,
85
- "model_q4f16.onnx": 3
86
- }
87
- }
88
- }
 
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
+ "dtype": "float16",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 2560,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 10240,
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
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention"
53
+ ],
54
+ "max_position_embeddings": 131072,
55
+ "model_type": "gemma3_text",
56
+ "num_attention_heads": 8,
57
+ "num_hidden_layers": 34,
58
+ "num_key_value_heads": 4,
59
+ "pad_token_id": 0,
60
+ "query_pre_attn_scalar": 256,
61
+ "rms_norm_eps": 1e-06,
62
+ "rope_local_base_freq": 10000,
63
+ "rope_parameters": {
64
+ "full_attention": {
65
+ "factor": 8.0,
66
+ "rope_type": "linear"
67
+ },
68
+ "sliding_attention": {
69
+ "rope_type": "default"
70
+ }
71
+ },
72
+ "rope_scaling": null,
73
+ "rope_theta": 1000000,
74
+ "sliding_window": 1024,
75
+ "transformers_version": "4.57.3",
76
+ "use_bidirectional_attention": false,
77
+ "use_cache": true,
78
+ "vocab_size": 262208,
79
+ "transformers.js_config": {
80
+ "kv_cache_dtype": "float16",
81
+ "use_external_data_format": {
82
+ "model_q4.onnx": 3,
83
+ "model_q4f16.onnx": 3
84
+ }
85
+ }
86
+ }