auto-patch README.md

uploaded from nethype/db2
2024-08-31 15:05:20 +00:00 · 2024-08-31 15:04:37 +00:00 · 2024-08-31 14:59:31 +00:00 · 2024-08-31 14:59:20 +00:00 · 2024-08-31 14:57:58 +00:00 · 2024-08-31 14:51:00 +00:00
11 changed files with 107 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -49,3 +49,12 @@ OpenCrystal-15B-L3-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 OpenCrystal-15B-L3-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
 OpenCrystal-15B-L3-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
 OpenCrystal-15B-L3-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
+OpenCrystal-15B-L3-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
--- a/OpenCrystal-15B-L3-v2.i1-IQ1_S.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-IQ1_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e0c135bc861cfb7e3ee2022a175af58777f2a8103ae22290d05b978a45cb78
+size 3497875552
--- a/OpenCrystal-15B-L3-v2.i1-IQ2_S.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-IQ2_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a3ed440499893af49b3aac7644b7ea67f41a357367869b418e67b3a2cf9333
+size 4922243168
--- a/OpenCrystal-15B-L3-v2.i1-IQ3_S.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-IQ3_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2748052755d96c2e2aca726b102a7a2df1e51910c8fa9d988cd24b20a79b5d05
+size 6700144736
--- a/OpenCrystal-15B-L3-v2.i1-IQ3_XS.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-IQ3_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d667e734cadef98ef09d1b1a7ab21b22fe2b923ca0c4209702055940d281b9
+size 6372989024
--- a/OpenCrystal-15B-L3-v2.i1-Q4_0.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba49cd93143e451f5451eb84799c077809aa87a978806b938e2f27b073a61ff
+size 8617506912
--- a/OpenCrystal-15B-L3-v2.i1-Q4_0_4_4.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-Q4_0_4_4.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1af5e2db00e0793445b1a289ece95315232e169e0ed52deab268b0712c553a
+size 8588146784
--- a/OpenCrystal-15B-L3-v2.i1-Q4_0_4_8.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-Q4_0_4_8.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b421a580ae61191665be99205a84c841b469602506e034f0a7349aa6f195488
+size 8588146784
--- a/OpenCrystal-15B-L3-v2.i1-Q4_0_8_8.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-Q4_0_8_8.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a25a4b14871b8096fcd8530db4eed44afe1794e7d59ffbd14ac84a00ac1a8012
+size 8588146784
--- a/OpenCrystal-15B-L3-v2.i1-Q5_K_M.gguf
+++ b/OpenCrystal-15B-L3-v2.i1-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab960347b570f0e5efcceeba65f0bb61a2d4b47ebbbb608532f4c046702a137
+size 10666031200
--- a/README.md
+++ b/README.md
@@ -1,6 +1,77 @@
+---
+base_model: Darkknight535/OpenCrystal-15B-L3-v2
+language:
+- en
+library_name: transformers
+quantized_by: mradermacher
+tags:
+- not-for-all-audiences
+---
+## About
+
 <!-- ### quantize_version: 2 -->
 <!-- ### output_tensor_quantised: 1 -->
 <!-- ### convert_type: hf -->
 <!-- ### vocab_type:  -->
 <!-- ### tags: nicoboss -->
 weighted/imatrix quants of https://huggingface.co/Darkknight535/OpenCrystal-15B-L3-v2
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-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/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.6 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.9 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 5.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 5.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q2_K.gguf) | i1-Q2_K | 5.8 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.5 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.1 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.7 | fast on arm, low quality |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.7 | fast on arm+i8mm, low quality |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.7 | fast on arm+sve, low quality |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q4_0.gguf) | i1-Q4_0 | 8.7 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.2 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/OpenCrystal-15B-L3-v2-i1-GGUF/resolve/main/OpenCrystal-15B-L3-v2.i1-Q6_K.gguf) | i1-Q6_K | 12.4 | 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
Michael Radermacher	a5c2cd71c7	auto-patch README.md	2024-08-31 15:05:20 +00:00
Michael Radermacher	567db9631d	uploaded from nethype/db2	2024-08-31 15:04:37 +00:00
Michael Radermacher	dd8b9425f9	uploaded from nethype/db2	2024-08-31 14:59:31 +00:00
Michael Radermacher	b6080ec189	uploaded from nethype/db2	2024-08-31 14:59:20 +00:00
Michael Radermacher	fef2f35d1a	uploaded from nethype/db2	2024-08-31 14:57:58 +00:00
Michael Radermacher	737c1c0610	uploaded from nethype/db2	2024-08-31 14:51:00 +00:00
Michael Radermacher	3e06778d37	uploaded from nethype/db2	2024-08-31 14:50:50 +00:00
Michael Radermacher	e9324e74b5	uploaded from nethype/db2	2024-08-31 14:44:35 +00:00
Michael Radermacher	512138d64d	uploaded from nethype/db2	2024-08-31 14:42:52 +00:00
Michael Radermacher	04e56f09b2	uploaded from nethype/db2	2024-08-31 14:40:40 +00:00