Hugging Face's logo

EricB
/
gemma-3-27b-it-UQFF

gemma3
uqff
mistral.rs
Model card Files
xet
Community
EricB HF Staff commited on
Commit
997a5fa
·
verified ·
1 Parent(s): 7cad307

Upload model

Browse files
Files changed (33) hide show
  1. .gitattributes +25 -0
  2. README.md +34 -0
  3. config.json +42 -0
  4. gemma3-27b-it-afq2-0.uqff +3 -0
  5. gemma3-27b-it-afq3-0.uqff +3 -0
  6. gemma3-27b-it-afq3-1.uqff +3 -0
  7. gemma3-27b-it-afq4-0.uqff +3 -0
  8. gemma3-27b-it-afq4-1.uqff +3 -0
  9. gemma3-27b-it-afq6-0.uqff +3 -0
  10. gemma3-27b-it-afq6-1.uqff +3 -0
  11. gemma3-27b-it-afq6-2.uqff +3 -0
  12. gemma3-27b-it-afq8-0.uqff +3 -0
  13. gemma3-27b-it-afq8-1.uqff +3 -0
  14. gemma3-27b-it-afq8-2.uqff +3 -0
  15. gemma3-27b-it-f8e4m3-0.uqff +3 -0
  16. gemma3-27b-it-f8e4m3-1.uqff +3 -0
  17. gemma3-27b-it-f8e4m3-2.uqff +3 -0
  18. gemma3-27b-it-q2k-0.uqff +3 -0
  19. gemma3-27b-it-q3k-0.uqff +3 -0
  20. gemma3-27b-it-q3k-1.uqff +3 -0
  21. gemma3-27b-it-q4k-0.uqff +3 -0
  22. gemma3-27b-it-q4k-1.uqff +3 -0
  23. gemma3-27b-it-q5k-0.uqff +3 -0
  24. gemma3-27b-it-q5k-1.uqff +3 -0
  25. gemma3-27b-it-q8_0-0.uqff +3 -0
  26. gemma3-27b-it-q8_0-1.uqff +3 -0
  27. gemma3-27b-it-q8_0-2.uqff +3 -0
  28. generation_config.json +13 -0
  29. preprocessor_config.json +29 -0
  30. processor_config.json +4 -0
  31. residual.safetensors +3 -0
  32. tokenizer.json +3 -0
  33. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,28 @@ 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
+ gemma3-27b-it-afq2-0.uqff filter=lfs diff=lfs merge=lfs -text
37
+ gemma3-27b-it-afq3-0.uqff filter=lfs diff=lfs merge=lfs -text
38
+ gemma3-27b-it-afq3-1.uqff filter=lfs diff=lfs merge=lfs -text
39
+ gemma3-27b-it-afq4-0.uqff filter=lfs diff=lfs merge=lfs -text
40
+ gemma3-27b-it-afq4-1.uqff filter=lfs diff=lfs merge=lfs -text
41
+ gemma3-27b-it-afq6-0.uqff filter=lfs diff=lfs merge=lfs -text
42
+ gemma3-27b-it-afq6-1.uqff filter=lfs diff=lfs merge=lfs -text
43
+ gemma3-27b-it-afq6-2.uqff filter=lfs diff=lfs merge=lfs -text
44
+ gemma3-27b-it-afq8-0.uqff filter=lfs diff=lfs merge=lfs -text
45
+ gemma3-27b-it-afq8-1.uqff filter=lfs diff=lfs merge=lfs -text
46
+ gemma3-27b-it-afq8-2.uqff filter=lfs diff=lfs merge=lfs -text
47
+ gemma3-27b-it-f8e4m3-0.uqff filter=lfs diff=lfs merge=lfs -text
48
+ gemma3-27b-it-f8e4m3-1.uqff filter=lfs diff=lfs merge=lfs -text
49
+ gemma3-27b-it-f8e4m3-2.uqff filter=lfs diff=lfs merge=lfs -text
50
+ gemma3-27b-it-q2k-0.uqff filter=lfs diff=lfs merge=lfs -text
51
+ gemma3-27b-it-q3k-0.uqff filter=lfs diff=lfs merge=lfs -text
52
+ gemma3-27b-it-q3k-1.uqff filter=lfs diff=lfs merge=lfs -text
53
+ gemma3-27b-it-q4k-0.uqff filter=lfs diff=lfs merge=lfs -text
54
+ gemma3-27b-it-q4k-1.uqff filter=lfs diff=lfs merge=lfs -text
55
+ gemma3-27b-it-q5k-0.uqff filter=lfs diff=lfs merge=lfs -text
56
+ gemma3-27b-it-q5k-1.uqff filter=lfs diff=lfs merge=lfs -text
57
+ gemma3-27b-it-q8_0-0.uqff filter=lfs diff=lfs merge=lfs -text
58
+ gemma3-27b-it-q8_0-1.uqff filter=lfs diff=lfs merge=lfs -text
59
+ gemma3-27b-it-q8_0-2.uqff filter=lfs diff=lfs merge=lfs -text
60
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - uqff
4
+ - mistral.rs
5
+ base_model: google/gemma-3-27b-it
6
+ base_model_relation: quantized
7
+ ---
8
+
9
+ <!-- Autogenerated from user input. -->
10
+
11
+ # `google/gemma-3-27b-it`, UQFF quantization
12
+
13
+
14
+ Run with [mistral.rs](https://github.com/EricLBuehler/mistral.rs). Documentation: [UQFF docs](https://github.com/EricLBuehler/mistral.rs/blob/master/docs/UQFF.md).
15
+
16
+ 1) **Flexible** 🌀: Multiple quantization formats in *one* file format with *one* framework to run them all.
17
+ 2) **Reliable** 🔒: Compatibility ensured with *embedded* and *checked* semantic versioning information from day 1.
18
+ 3) **Easy** 🤗: Download UQFF models *easily* and *quickly* from Hugging Face, or use a local file.
19
+ 3) **Customizable** 🛠️: Make and publish your own UQFF files in minutes.
20
+
21
+ ## Examples
22
+ |Quantization type(s)|Example|
23
+ |--|--|
24
+ |AFQ2|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f gemma3-27b-it-afq2-0.uqff`|
25
+ |AFQ3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq3-0.uqff;gemma3-27b-it-afq3-1.uqff"`|
26
+ |AFQ4|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq4-0.uqff;gemma3-27b-it-afq4-1.uqff"`|
27
+ |AFQ6|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq6-0.uqff;gemma3-27b-it-afq6-1.uqff;gemma3-27b-it-afq6-2.uqff"`|
28
+ |AFQ8|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-afq8-0.uqff;gemma3-27b-it-afq8-1.uqff;gemma3-27b-it-afq8-2.uqff"`|
29
+ |F8E4M3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-f8e4m3-0.uqff;gemma3-27b-it-f8e4m3-1.uqff;gemma3-27b-it-f8e4m3-2.uqff"`|
30
+ |Q2K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f gemma3-27b-it-q2k-0.uqff`|
31
+ |Q3K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q3k-0.uqff;gemma3-27b-it-q3k-1.uqff"`|
32
+ |Q4K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q4k-0.uqff;gemma3-27b-it-q4k-1.uqff"`|
33
+ |Q5K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q5k-0.uqff;gemma3-27b-it-q5k-1.uqff"`|
34
+ |Q8_0|`./mistralrs-server -i vision-plain -m EricB/gemma-3-27b-it-UQFF -f "gemma3-27b-it-q8_0-0.uqff;gemma3-27b-it-q8_0-1.uqff;gemma3-27b-it-q8_0-2.uqff"`|
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
+ "image_token_index": 262144,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "text_config": {
16
+ "head_dim": 128,
17
+ "hidden_size": 5376,
18
+ "intermediate_size": 21504,
19
+ "model_type": "gemma3_text",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 62,
22
+ "num_key_value_heads": 16,
23
+ "query_pre_attn_scalar": 168,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "rope_type": "linear"
27
+ },
28
+ "sliding_window": 1024
29
+ },
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.50.0.dev0",
32
+ "vision_config": {
33
+ "hidden_size": 1152,
34
+ "image_size": 896,
35
+ "intermediate_size": 4304,
36
+ "model_type": "siglip_vision_model",
37
+ "num_attention_heads": 16,
38
+ "num_hidden_layers": 27,
39
+ "patch_size": 14,
40
+ "vision_use_head": false
41
+ }
42
+ }
gemma3-27b-it-afq2-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca2428e1d82fb743c3eca214fa1491cf24cb187aa1e610a32ea83d900995925
3
+ size 8440060972
gemma3-27b-it-afq3-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d8c6e450f00616a9abeca754da60ebe839dadc232b60afdb5eb80f27341414
3
+ size 10732252284
gemma3-27b-it-afq3-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60297ce7c54b59be745457a9c86371a52a16d0ef06739ea1abc9f9a470d417c3
3
+ size 1083807664
gemma3-27b-it-afq4-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30803fedea5f36d5bd54894629d55873f7d6acb4d07f480b8bdd8f3befacebd7
3
+ size 10714390580
gemma3-27b-it-afq4-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db48b502c703c185a08734cf2c36ef3341bcb50b1f4994fa86d575f499b015f
3
+ size 4477668496
gemma3-27b-it-afq6-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0461d3d3555fa7837caec223c3a89e626cf22b84fdd1863b4d4fc2db5578209
3
+ size 10685904760
gemma3-27b-it-afq6-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c9c6551e85b7eca0f9f5122f9bbd131a0bbb479c58852e61ad0fcbd81666c8
3
+ size 10734829656
gemma3-27b-it-afq6-2.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3d0ec41bd797a623fdb13b4b9c894b6f2b612dcb7a54d67a74f7dca66c6d6a
3
+ size 523322652
gemma3-27b-it-afq8-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23a506057b1acdf83e5bce3735173eb4210076d3da3bd41333639bd7f88ccc2
3
+ size 10733463932
gemma3-27b-it-afq8-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99e8b8ad6d675ae3f86b26c165ddcff60f688956ccaaada088aa1dd8515bfb3
3
+ size 10698007296
gemma3-27b-it-afq8-2.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ca2847a253bbeed36ed20fd0100056901792d247d5b6be62a48aa26d2d183e
3
+ size 7264584080
gemma3-27b-it-f8e4m3-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:054209ca2c00e6efd2941cb7a7167925875cf0eec58995866b40e7b4270c4813
3
+ size 10674604944
gemma3-27b-it-f8e4m3-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b34d4118c28663a43d06e1687a436def6a50383d98859152e94fb0f5ec95d6e2
3
+ size 10734818900
gemma3-27b-it-f8e4m3-2.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6103a8ffe3c4f540e7078a5321f63c656059d45416a5b3d99dd9ae06ba2e4c27
3
+ size 5598620674
gemma3-27b-it-q2k-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4edcb1bda06cbaf2a3cb03ff246a899d9c58736c642579489ef1d41a50ed6110
3
+ size 8862042574
gemma3-27b-it-q3k-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a80c469c9dfb23adf1cb00768a1a491e90df9194e20e371aebc5bb621da5c9
3
+ size 10736921998
gemma3-27b-it-q3k-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ecdaf10dedf5916847e3c17d1e23c18cabac083ce45f5bbfbd58ee1a82e8734
3
+ size 868119760
gemma3-27b-it-q4k-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c538d3cbcb3182fa69d70acb0535d2236295b257fcae8cc86b4281001e2d350e
3
+ size 10714377938
gemma3-27b-it-q4k-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff57d06ba3a5e59cc24c237163c51b9292815e44a4d76a9dc5baa913c106b0d
3
+ size 4477662868
gemma3-27b-it-q5k-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbd7e0010533697f81506108fc5bc6cff62bd6385676c45f12ea326a037f64a
3
+ size 10665557782
gemma3-27b-it-q5k-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d922209e713d484f0c6f5c73abe897dee221774a2ba77071edf7a4be6bd68f1
3
+ size 7902482016
gemma3-27b-it-q8_0-0.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384ea97d37e989feb84d8e903eefe942fbbabf09bd2def19fd69377f426da189
3
+ size 10733457674
gemma3-27b-it-q8_0-1.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a664b1776611b9cde136360359c39649b9093242f40bf172878004a485141115
3
+ size 10698000072
gemma3-27b-it-q8_0-2.uqff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f41b6043ebfe36f4793d6de199a4138c738a839ada5e5c0901ed9849ea83ca0
3
+ size 7264579292
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": "4.50.0.dev0"
13
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
residual.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba5d046dcf72e99919424172bfbb0e5ff7dddc6aecbcb0f536b3c2a9e485778f
3
+ size 3668199976
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a4672a51a9f582918ab48639e47c6cf053961c0bb6c6e6e32479f1ff123322
3
+ size 33384604
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff