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
+gemma3-1b-it-afq2-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-afq3-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-afq4-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-afq6-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-afq8-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-f8e4m3-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-q2k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-q3k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-q4k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-q5k-0.uqff filter=lfs diff=lfs merge=lfs -text
+gemma3-1b-it-q8_0-0.uqff filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,34 @@
+---
+tags:
+  - uqff
+  - mistral.rs
+base_model: google/gemma-3-1b-it
+base_model_relation: quantized
+---
+
+<!-- Autogenerated from user input. -->
+
+# `google/gemma-3-1b-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-3-1b-it-UQFF -f gemma3-1b-it-afq2-0.uqff`|
+|AFQ3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq3-0.uqff`|
+|AFQ4|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq4-0.uqff`|
+|AFQ6|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq6-0.uqff`|
+|AFQ8|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq8-0.uqff`|
+|F8E4M3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-f8e4m3-0.uqff`|
+|Q2K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q2k-0.uqff`|
+|Q3K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q3k-0.uqff`|
+|Q4K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q4k-0.uqff`|
+|Q5K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q5k-0.uqff`|
+|Q8_0|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q8_0-0.uqff`|

README.md

@@ -0,0 +1,34 @@
+---
+tags:
+  - uqff
+  - mistral.rs
+base_model: google/gemma-3-1b-it
+base_model_relation: quantized
+---
+
+<!-- Autogenerated from user input. -->
+
+# `google/gemma-3-1b-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-3-1b-it-UQFF -f gemma3-1b-it-afq2-0.uqff`|
+|AFQ3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq3-0.uqff`|
+|AFQ4|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq4-0.uqff`|
+|AFQ6|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq6-0.uqff`|
+|AFQ8|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-afq8-0.uqff`|
+|F8E4M3|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-f8e4m3-0.uqff`|
+|Q2K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q2k-0.uqff`|
+|Q3K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q3k-0.uqff`|
+|Q4K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q4k-0.uqff`|
+|Q5K|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q5k-0.uqff`|
+|Q8_0|`./mistralrs-server -i vision-plain -m EricB/gemma-3-1b-it-UQFF -f gemma3-1b-it-q8_0-0.uqff`|

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "use_cache": true,
+  "vocab_size": 262144
+}

gemma3-1b-it-afq2-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d41b52dbaf9bc743ae5c5b1e955bfc96d86cfd460c682db0b2f9e411bfa91a
+size 312448476

gemma3-1b-it-afq3-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05f7004b57ab4f444a0b6cb9bc2255669ed913c116107d8deaa2fd2a44c0d86
+size 437417508

gemma3-1b-it-afq4-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede1d02717ad608379336a912a6cad2ab6bfe8534f05c1d31dc90b944150cdf8
+size 562386468

gemma3-1b-it-afq6-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c75ec53a89ba9335246aea2fe0eec0c7850b7de5736e30dbfc9d3d7dbe8a39
+size 812324388

gemma3-1b-it-afq8-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37492b25149cf0337906dfd5eeabc63819f68427b3b9198569090b009b57ea5c
+size 1062262388

gemma3-1b-it-f8e4m3-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3292f96abe5d3259d86a49be19fee76d7c73763fdb912de848e86a90126fc79
+size 999773118

gemma3-1b-it-q2k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82702639ae85a9e2551051d36ef43f1d549493ef51f1131ac33d9de3139c5cb9
+size 506668062

gemma3-1b-it-q3k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4685f79d061d74780669902ae70e091ded26b015bb5df45edf1496f4cd04ab4f
+size 530809374

gemma3-1b-it-q4k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefdb760915b3c837b41ae848034602d8a6c6e99bfaa1998a9888c4f749e2f81
+size 610007070

gemma3-1b-it-q5k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e179145e7d51b9706dbab8b45bc02ad002ed367227dec15d73f7a2c43fc63f61
+size 687347742

gemma3-1b-it-q8_0-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b82948898a73f521457c82c7fc0f14f53c7a2d69a1f9c2b7a29410e77d8e46
+size 1062254702

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"
+}

residual.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0c40ccd7c8e165cdc32f69df1d8ef402a22670d02bd2f7c576ed64643bf19af
+size 604266400

tokenizer.json

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