auto-patch README.md

uploaded from rain
2024-12-13 03:23:35 +00:00 · 2024-12-13 03:09:08 +00:00 · 2024-12-13 03:02:41 +00:00 · 2024-12-13 02:55:46 +00:00 · 2024-12-13 02:53:36 +00:00 · 2024-12-13 02:48:51 +00:00
11 changed files with 109 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -47,3 +47,12 @@ Aura-4B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 Aura-4B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
 Aura-4B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 Aura-4B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Aura-4B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Aura-4B.i1-IQ1_S.gguf
+++ b/Aura-4B.i1-IQ1_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d34a74911f677a3b8cc63b91ddad366a8a0bd192ce59cf4d6cb0e7ffd409ba5
+size 1213414080
--- a/Aura-4B.i1-IQ2_S.gguf
+++ b/Aura-4B.i1-IQ2_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994328b9e955f0153fa331f03f939efed17985cb2ae034ebe3df69da673386c4
+size 1625510592
--- a/Aura-4B.i1-IQ2_XS.gguf
+++ b/Aura-4B.i1-IQ2_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d2d8a71f28227d832299514473ea5de824687d5d4bd7321d6538401ad4b30c
+size 1517370048
--- a/Aura-4B.i1-IQ3_S.gguf
+++ b/Aura-4B.i1-IQ3_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ac2ea0377269a701161d456d2d6deb5c8cf5bf96df6e4c5d7b2a5f73e5c028
+size 2114898624
--- a/Aura-4B.i1-IQ3_XS.gguf
+++ b/Aura-4B.i1-IQ3_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97772359a5fe1b4e8f7b9f521408f0a9dadf91006e882c4623632ad88e2c186
+size 2027604672
--- a/Aura-4B.i1-Q3_K_L.gguf
+++ b/Aura-4B.i1-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ee68fe5e0987bc5eabd8ce4715006e738bed87de9fde53b3ff46ab80f6ea31
+size 2464860864
--- a/Aura-4B.i1-Q4_0.gguf
+++ b/Aura-4B.i1-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4156a5eebce3ea569b5d6ba355615f63ff7d1dda9e5d7cf2855e9a36b69b2525
+size 2655601344
--- a/Aura-4B.i1-Q5_K_M.gguf
+++ b/Aura-4B.i1-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5083cd6d6cdedc7298d00083b9932f654fdcac49d2650a56ddf98b756489543c
+size 3230188224
--- a/Aura-4B.i1-Q5_K_S.gguf
+++ b/Aura-4B.i1-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac033e0cf48cfe38015737e40ded6b179c1d1b65b58ddfc6e31bd596412d9da8
+size 3163341504
--- a/README.md
+++ b/README.md
@@ -1,6 +1,79 @@
+---
+base_model: AuraIndustries/Aura-4B
+datasets:
+- Mielikki/Erebus-87k
+- FourOhFour/Instruct_Phase
+- FourOhFour/RP_Phase
+- anthracite-core/full-opus-chosen-hermes-rejected-kto-v1
+language:
+- en
+library_name: transformers
+license: apache-2.0
+quantized_by: mradermacher
+---
+## About
+
 <!-- ### quantize_version: 2 -->
 <!-- ### output_tensor_quantised: 1 -->
 <!-- ### convert_type: hf -->
 <!-- ### vocab_type:  -->
 <!-- ### tags: nicoboss -->
 weighted/imatrix quants of https://huggingface.co/AuraIndustries/Aura-4B
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/Aura-4B-GGUF
+## Usage
+
+If you are unsure how to use GGUF files, refer to one of [TheBloke's
+READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
+more details, including on how to concatenate multi-part files.
+
+## Provided Quants
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.0 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ3_M.gguf) | i1-IQ3_M | 2.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.4 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.6 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q4_0.gguf) | i1-Q4_0 | 2.8 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.8 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.9 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Aura-4B-i1-GGUF/resolve/main/Aura-4B.i1-Q6_K.gguf) | i1-Q6_K | 3.8 | practically like static Q6_K |
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
+
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+
+## FAQ / Model Request
+
+See https://huggingface.co/mradermacher/model_requests for some answers to
+questions you might have and/or if you want some other model quantized.
+
+## Thanks
+
+I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
+me use its servers and providing upgrades to my workstation to enable
+this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
+
+<!-- end -->
Author	SHA1	Message	Date
team mradermacher	b1e0e8752e	auto-patch README.md	2024-12-13 03:23:35 +00:00
team mradermacher	8cc3c974b8	uploaded from rain	2024-12-13 03:09:08 +00:00
team mradermacher	24d4d8a602	uploaded from rain	2024-12-13 03:02:41 +00:00
team mradermacher	3cfdcbb366	uploaded from rain	2024-12-13 02:55:46 +00:00
team mradermacher	e3c76a74ac	uploaded from rain	2024-12-13 02:53:36 +00:00
team mradermacher	148c3cccd7	uploaded from rain	2024-12-13 02:48:51 +00:00
team mradermacher	5775bf4284	uploaded from rain	2024-12-13 02:44:33 +00:00
team mradermacher	6351391f2e	uploaded from rain	2024-12-13 02:30:38 +00:00
team mradermacher	f2c366df01	uploaded from rain	2024-12-13 02:25:59 +00:00
team mradermacher	17cb8bfe1b	uploaded from rain	2024-12-13 02:11:11 +00:00