Upload model

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-afq2-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-afq3-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-afq4-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-afq6-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-afq8-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-f8e4m3-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-q2k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-q3k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-q4k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-q5k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-4b-it-q8_0-0.uqff filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+tags:
+  - uqff
+  - mistral.rs
+base_model: google/gemma-3-4b-it
+base_model_relation: quantized
+---
+
+<!-- Autogenerated from user input. -->
+
+# `google/gemma-3-4b-it`, UQFF quantization
+
+
+Run with [mistral.rs](https://github.com/EricLBuehler/mistral.rs). Documentation: [UQFF docs](https://github.com/EricLBuehler/mistral.rs/blob/master/docs/UQFF.md).
+
+1) **Flexible** 🌀: Multiple quantization formats in *one* file format with *one* framework to run them all.
+2) **Reliable** 🔒: Compatibility ensured with *embedded* and *checked* semantic versioning information from day 1.
+3) **Easy** 🤗: Download UQFF models *easily* and *quickly* from Hugging Face, or use a local file.
+3) **Customizable** 🛠️: Make and publish your own UQFF files in minutes.
+
+## Examples
+|Quantization type(s)|Example|
+|--|--|
+|AFQ2|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-afq2-0.uqff`|
+|AFQ3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-afq3-0.uqff`|
+|AFQ4|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-afq4-0.uqff`|
+|AFQ6|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-afq6-0.uqff`|
+|AFQ8|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-afq8-0.uqff`|
+|F8E4M3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-f8e4m3-0.uqff`|
+|Q2K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-q2k-0.uqff`|
+|Q3K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-q3k-0.uqff`|
+|Q4K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-q4k-0.uqff`|
+|Q5K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-q5k-0.uqff`|
+|Q8_0|`./mistralrs-server -i vision-plain -m EricB/gemma-3-4b-it-UQFF -f gemma3-4b-it-q8_0-0.uqff`|

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "hidden_size": 2560,
+    "intermediate_size": 10240,
+    "model_type": "gemma3_text",
+    "num_hidden_layers": 34,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "sliding_window": 1024
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

gemma3-4b-it-afq2-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd4da935e4a4643265e4a2faa69a5beda8fbe043646ee4414f83235f5177ea4
+size 1212501540

gemma3-4b-it-afq3-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eda4c491c5b28fc15f99b2d855c25254f12ab6d360750e148b9e1e3b7a2f516
+size 1697488724

gemma3-4b-it-afq4-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ec12d5c4ce731a259245a3978e5caa1ab482160311f3fa321b14a6df3c53c1
+size 2182475684

gemma3-4b-it-afq6-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398aeedf5048fc3ac09210ba3cc1120766fcd33edcf99cf85757b81d38a795f3
+size 3152449524

gemma3-4b-it-afq8-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1749869931a1d89294655bb95fac86358a3a978835593798d0b77d2573f03090
+size 4122423324

gemma3-4b-it-f8e4m3-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d94e158247d6a4d4f70785d2e864653cc66ba78febe2cfc308234478c65642a
+size 3879923662

gemma3-4b-it-q2k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7485733a89779463dd130963da9a182ed0e048e0b0e5170fdbbcc02ae3a5a0
+size 1273114886

gemma3-4b-it-q3k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07b1e98d893331ac077e409240faa2cc54f13247c69972e518392e1f88efad4
+size 1667167006

gemma3-4b-it-q4k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3e3af19315a00229b6b4aeca1b7b1db061127575a360a79e38e097987b9e77
+size 2182465646

gemma3-4b-it-q5k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6e3e7eceeb9ed1133f31e0b768cab3ac2235423ae760355103444acf7cb3ea
+size 2667452574

gemma3-4b-it-q8_0-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee927648a2e8d1f2d6059867d24edd342735dffc65ad343e3eac084d8bf8647
+size 4122413286

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.50.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

residual.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0ea96131be74e2b699f2cb5ec4e44a1231ab94c5a2cd622bcb965822267dcb
+size 2182961544

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a4672a51a9f582918ab48639e47c6cf053961c0bb6c6e6e32479f1ff123322
+size 33384604