Hugging Face's logo

FastFlowLM
/
Embedding-Gemma-300M-NPU2

Sentence Similarity
sentence-transformers
gemma3_text
feature-extraction
text-embeddings-inference
Model card Files
xet
 Community
FastFlowLM commited on
Commit
2909896
·
verified ·
1 Parent(s): a164777

feat: init upload

Browse files
Files changed (9) hide show
  1. .gitattributes +6 -0
  2. attn_full_mask.xclbin +3 -0
  3. config.json +60 -0
  4. mm.xclbin +3 -0
  5. model.q4nx +3 -0
  6. mv.xclbin +3 -0
  7. sliding_attn.xclbin +3 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ attn_full_mask.xclbin filter=lfs diff=lfs merge=lfs -text
37
+ mm.xclbin filter=lfs diff=lfs merge=lfs -text
38
+ model.q4nx filter=lfs diff=lfs merge=lfs -text
39
+ mv.xclbin filter=lfs diff=lfs merge=lfs -text
40
+ sliding_attn.xclbin filter=lfs diff=lfs merge=lfs -text
41
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
attn_full_mask.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206767cadc58bb098abde7e47532637a4d2c31412081c1b0a1633aac79e20b5c
3
+ size 274427
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": "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
+ "transformers_version": "4.57.0.dev0",
57
+ "use_bidirectional_attention": true,
58
+ "use_cache": true,
59
+ "vocab_size": 262144
60
+ }
mm.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5a03b532daae5ac30c4e9a02ff080e3928f68b8f4465c0a7e1e11c8e552482
3
+ size 175499
model.q4nx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2ecad094d1013b440820a8bc880aeb180972bc2aee1117626850620f791024
3
+ size 615197168
mv.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed93c4ad20dd2e646181db4256fc59cb54d8a7b415ba15a5dd2637e812835f9
3
+ size 129627
sliding_attn.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72752ba1fa0ee75f4ff03660993419b6c57d58a597ed701921219e319a55c6f5
3
+ size 269307
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6852f8d561078cc0cebe70ca03c5bfdd0d60a45f9d2e0e1e4cc05b68e9ec329e
3
+ size 33385008
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff