Hugging Face's logo

microvnn
/
onnx_convert

ONNX
Model card Files
xet
Community
microvnn commited on
Commit
9f1b65e
·
verified ·
1 Parent(s): ab8613d

Delete embeddings/embedding_gemma_300m_int8

Browse files
Files changed (9) hide show
  1. embeddings/embedding_gemma_300m_int8/added_tokens.json +0 -3
  2. embeddings/embedding_gemma_300m_int8/config.json +0 -62
  3. embeddings/embedding_gemma_300m_int8/model_bf16_quantized.onnx +0 -3
  4. embeddings/embedding_gemma_300m_int8/model_quantized.onnx +0 -3
  5. embeddings/embedding_gemma_300m_int8/ort_config.json +0 -33
  6. embeddings/embedding_gemma_300m_int8/special_tokens_map.json +0 -33
  7. embeddings/embedding_gemma_300m_int8/tokenizer.json +0 -3
  8. embeddings/embedding_gemma_300m_int8/tokenizer.model +0 -3
  9. embeddings/embedding_gemma_300m_int8/tokenizer_config.json +0 -0
embeddings/embedding_gemma_300m_int8/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
 
 
 
embeddings/embedding_gemma_300m_int8/config.json DELETED
@@ -1,62 +0,0 @@
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
- "cache_implementation": "hybrid",
11
- "dtype": "float32",
12
- "eos_token_id": 1,
13
- "final_logit_softcapping": null,
14
- "head_dim": 256,
15
- "hidden_activation": "gelu_pytorch_tanh",
16
- "hidden_size": 768,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 1152,
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
- ],
45
- "max_position_embeddings": 2048,
46
- "model_type": "gemma3_text",
47
- "num_attention_heads": 3,
48
- "num_hidden_layers": 24,
49
- "num_key_value_heads": 1,
50
- "pad_token_id": 0,
51
- "query_pre_attn_scalar": 256,
52
- "rms_norm_eps": 1e-06,
53
- "rope_local_base_freq": 10000.0,
54
- "rope_scaling": null,
55
- "rope_theta": 1000000.0,
56
- "sliding_window": 512,
57
- "sliding_window_pattern": 6,
58
- "transformers_version": "4.51.3",
59
- "use_bidirectional_attention": true,
60
- "use_cache": true,
61
- "vocab_size": 262144
62
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
embeddings/embedding_gemma_300m_int8/model_bf16_quantized.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6697c1e1fbc3b723ab41f5873797049b4c249a842160aacdeca3249ab178d8fb
3
- size 309900951
 
 
 
 
embeddings/embedding_gemma_300m_int8/model_quantized.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5473f9d1af3f3ec16216572775b88acbd329aeaf2e09b534f0af2ab34453bf91
3
- size 310076236
 
 
 
 
embeddings/embedding_gemma_300m_int8/ort_config.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "one_external_file": true,
3
- "opset": null,
4
- "optimization": {},
5
- "quantization": {
6
- "activations_dtype": "QUInt8",
7
- "activations_symmetric": false,
8
- "format": "QOperator",
9
- "is_static": false,
10
- "mode": "IntegerOps",
11
- "nodes_to_exclude": [],
12
- "nodes_to_quantize": [],
13
- "operators_to_quantize": [
14
- "Conv",
15
- "MatMul",
16
- "Attention",
17
- "LSTM",
18
- "Gather",
19
- "Transpose",
20
- "EmbedLayerNormalization"
21
- ],
22
- "per_channel": false,
23
- "qdq_add_pair_to_weight": false,
24
- "qdq_dedicated_pair": false,
25
- "qdq_op_type_per_channel_support_to_axis": {
26
- "MatMul": 1
27
- },
28
- "reduce_range": false,
29
- "weights_dtype": "QInt8",
30
- "weights_symmetric": true
31
- },
32
- "use_external_data_format": false
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
embeddings/embedding_gemma_300m_int8/special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
embeddings/embedding_gemma_300m_int8/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6852f8d561078cc0cebe70ca03c5bfdd0d60a45f9d2e0e1e4cc05b68e9ec329e
3
- size 33385008
 
 
 
 
embeddings/embedding_gemma_300m_int8/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
- size 4689074
 
 
 
 
embeddings/embedding_gemma_300m_int8/tokenizer_config.json DELETED
The diff for this file is too large to render. See raw diff