Hugging Face's logo

aixk
/
BAAR2-3M

Text Generation
Safetensors
fhn_concept_gau
baar2
3m
multilingual
ultra-lightweight
edge-ai
rag
Model card Files
xet
 Community
aixk commited on
Commit
aaf1f48
·
1 Parent(s): 076925d

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +14 -0
  2. config.json +16 -0
  3. model.safetensors +3 -0
  4. model.vlite +3 -0
  5. model_full_int1.vlite +3 -0
  6. model_full_int2.vlite +3 -0
  7. model_full_int3.vlite +3 -0
  8. model_full_int4.vlite +3 -0
  9. model_micro_int1.vlite +3 -0
  10. model_micro_int2.vlite +3 -0
  11. model_micro_int3.vlite +3 -0
  12. model_micro_int4.vlite +3 -0
  13. model_shared.vlite +3 -0
  14. model_shared_int1.vlite +3 -0
  15. model_shared_int2.vlite +3 -0
  16. model_shared_int3.vlite +3 -0
  17. model_shared_int4.vlite +3 -0
  18. tokenizer_state.json +0 -0
  19. vlite_manifest.json +39 -0
.gitattributes CHANGED
@@ -33,3 +33,17 @@ 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
+ model.vlite filter=lfs diff=lfs merge=lfs -text
37
+ model_full_int1.vlite filter=lfs diff=lfs merge=lfs -text
38
+ model_full_int2.vlite filter=lfs diff=lfs merge=lfs -text
39
+ model_full_int3.vlite filter=lfs diff=lfs merge=lfs -text
40
+ model_full_int4.vlite filter=lfs diff=lfs merge=lfs -text
41
+ model_micro_int1.vlite filter=lfs diff=lfs merge=lfs -text
42
+ model_micro_int2.vlite filter=lfs diff=lfs merge=lfs -text
43
+ model_micro_int3.vlite filter=lfs diff=lfs merge=lfs -text
44
+ model_micro_int4.vlite filter=lfs diff=lfs merge=lfs -text
45
+ model_shared.vlite filter=lfs diff=lfs merge=lfs -text
46
+ model_shared_int1.vlite filter=lfs diff=lfs merge=lfs -text
47
+ model_shared_int2.vlite filter=lfs diff=lfs merge=lfs -text
48
+ model_shared_int3.vlite filter=lfs diff=lfs merge=lfs -text
49
+ model_shared_int4.vlite filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FHN_T4Max_150M"
4
+ ],
5
+ "model_type": "fhn_concept_gau",
6
+ "hidden_size": 256,
7
+ "expansion_dim": 512,
8
+ "attn_dim": 76,
9
+ "num_hidden_layers": 8,
10
+ "vocab_size": 1536,
11
+ "concept_size": 768,
12
+ "max_position_embeddings": 512,
13
+ "logit_soft_capping": 50.0,
14
+ "torch_dtype": "float16",
15
+ "transformers_version": "4.44.0"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e00a8b2d640296ab9031836adca6f1b20a43d0406a71dbe2c9bcd7a6508044
3
+ size 8764776
model.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a864fcbac057ac9e796d2875cebd8769ae542a24d27193b4bd57f7bda3de292
3
+ size 2024770
model_full_int1.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f80fc02b70a335c3f28e88ae70a05f8b391878199c2401c2f6201d71de530f
3
+ size 1190480
model_full_int2.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab480ac293579bce38dbc4baea26a155505b07a8de55dc782a02945383e75e6
3
+ size 1622608
model_full_int3.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7d889f9b32fa0f2f5341e60a986933dc2119b406a3d10ea10c0c5162692de0
3
+ size 2054720
model_full_int4.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5177399497c13fa8cbfbd3a0e50a34b5103ddd099f1107173fa1037dbb77f9
3
+ size 2486864
model_micro_int1.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d30f7192edc904dd3b995531ce5fb21c56b7e3aa955887e2725467ea16471cd
3
+ size 1858648
model_micro_int2.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a864fcbac057ac9e796d2875cebd8769ae542a24d27193b4bd57f7bda3de292
3
+ size 2024770
model_micro_int3.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a012b76ce139bd7a842388367ae00121542c6d19daa7103b97c66bfc05518d
3
+ size 2170823
model_micro_int4.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d50754b17ad966660d4dc1ebcbf397cf719cd67d8baa539effacbf7b022809
3
+ size 2287886
model_shared.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cd749301ac5a0e1c7a9a619cc7a23fca6f2eb5c87ff2a7ab6ed025ace5de61
3
+ size 1400752
model_shared_int1.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78dba25c41d16c65022a83aa1f4a3f3131e4187e3cbd5bd7ae5f91e0c163dfde
3
+ size 752576
model_shared_int2.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ad53419bd55225a8d06b93781315264c456f1aac0f63f861b386ed743775b5
3
+ size 968640
model_shared_int3.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:598c90c865d02c660fbf1a48bfe071d70c8f7bd06b3d7caa1ef27d4faaab5307
3
+ size 1184688
model_shared_int4.vlite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cd749301ac5a0e1c7a9a619cc7a23fca6f2eb5c87ff2a7ab6ed025ace5de61
3
+ size 1400752
tokenizer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
vlite_manifest.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "FHN-T4Max-ConceptTransformer-150M",
3
+ "description": "Universal Cross-Lingual Concept Model with SafeTensors & VLite 1~4 bit quantization",
4
+ "default_web_model": "model.vlite (Micro Mixed-INT2, ~25.8MB, >90% Quality)",
5
+ "safetensors_file": "model.safetensors",
6
+ "lineups": {
7
+ "full_18l": [
8
+ "model_full_int1.vlite",
9
+ "model_full_int2.vlite",
10
+ "model_full_int3.vlite",
11
+ "model_full_int4.vlite"
12
+ ],
13
+ "shared_8x2": [
14
+ "model_shared_int1.vlite",
15
+ "model_shared_int2.vlite",
16
+ "model_shared_int3.vlite",
17
+ "model_shared_int4.vlite"
18
+ ],
19
+ "micro_gau_zlib": [
20
+ "model_micro_int1.vlite",
21
+ "model_micro_int2.vlite",
22
+ "model_micro_int3.vlite",
23
+ "model_micro_int4.vlite"
24
+ ]
25
+ },
26
+ "languages": [
27
+ "ko",
28
+ "en",
29
+ "ja",
30
+ "zh",
31
+ "es",
32
+ "pt",
33
+ "de",
34
+ "ru",
35
+ "hi",
36
+ "vi",
37
+ "th"
38
+ ]
39
+ }