auto-patch README.md

uploaded from nethype/db2
2024-05-14 15:38:49 +00:00 · 2024-05-14 15:32:37 +00:00 · 2024-05-14 15:28:14 +00:00 · 2024-05-14 15:24:30 +00:00 · 2024-05-14 15:23:20 +00:00 · 2024-05-14 15:22:01 +00:00
11 changed files with 100 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -39,3 +39,12 @@ Med-ChimeraLlama-3-8B_SHERP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 Med-ChimeraLlama-3-8B_SHERP.f16.gguf filter=lfs diff=lfs merge=lfs -text
 Med-ChimeraLlama-3-8B_SHERP.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
 Med-ChimeraLlama-3-8B_SHERP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Med-ChimeraLlama-3-8B_SHERP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Med-ChimeraLlama-3-8B_SHERP.IQ3_XS.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.IQ3_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad66c91f8bdd6a1104d4122778ae6421ae82d8fa762f529a839143ea70716359
+size 3518746944
--- a/Med-ChimeraLlama-3-8B_SHERP.IQ4_XS.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25847d7fbe5344e2f64058dae6acb8c489718a84e8972b640e19951d43084c45
+size 4484362560
--- a/Med-ChimeraLlama-3-8B_SHERP.Q3_K_L.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea98ee75426ec50f4f596f09603efce2cd214ae81098b2d822ac2d3908d1dc3a
+size 4321956160
--- a/Med-ChimeraLlama-3-8B_SHERP.Q3_K_M.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2249f0200c1ec2894632bac90d92bc254695fca0d5a582f4553682ca643156
+size 4018917696
--- a/Med-ChimeraLlama-3-8B_SHERP.Q3_K_S.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f301ae1e55a82a164a02d1ba6f2bb5aa6a99c121d20a775fcb354519bdd626
+size 3664499008
--- a/Med-ChimeraLlama-3-8B_SHERP.Q4_K_M.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f543384ce4ff61fb05aefb3d8a5624b8550ecd53c62b69ad0092fb5b1132f27a
+size 4920734016
--- a/Med-ChimeraLlama-3-8B_SHERP.Q5_K_M.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96bf0836eeae82fcec170f874e1f0d90477a0ac18acb542739f0b44d1a1f8d73
+size 5732987200
--- a/Med-ChimeraLlama-3-8B_SHERP.Q5_K_S.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5fe7bae97b71f46a65e037da28e2d05dc8165e010ce25adc8716cc52291de6
+size 5599293760
--- a/Med-ChimeraLlama-3-8B_SHERP.Q6_K.gguf
+++ b/Med-ChimeraLlama-3-8B_SHERP.Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db002a0b1dcb1880614df0ade79cbb45d35268081cb8b9af95c8cfd7da8d269
+size 6596006208
--- a/README.md
+++ b/README.md
@@ -1,5 +1,69 @@
+---
+base_model: ChenWeiLi/Med-ChimeraLlama-3-8B_SHERP
+language:
+- en
+library_name: transformers
+license: llama3
+quantized_by: mradermacher
+tags:
+- mergekit
+- merge
+---
+## About
+
 <!-- ### quantize_version: 2 -->
 <!-- ### output_tensor_quantised: 1 -->
 <!-- ### convert_type: hf -->
 <!-- ### vocab_type:  -->
 static quants of https://huggingface.co/ChenWeiLi/Med-ChimeraLlama-3-8B_SHERP
+
+<!-- provided-files -->
+weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
+## 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/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q2_K.gguf) | Q2_K | 3.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.IQ3_XS.gguf) | IQ3_XS | 3.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q3_K_S.gguf) | Q3_K_S | 3.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.IQ3_M.gguf) | IQ3_M | 3.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q3_K_L.gguf) | Q3_K_L | 4.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.IQ4_XS.gguf) | IQ4_XS | 4.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q5_K_S.gguf) | Q5_K_S | 5.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q5_K_M.gguf) | Q5_K_M | 5.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Med-ChimeraLlama-3-8B_SHERP-GGUF/resolve/main/Med-ChimeraLlama-3-8B_SHERP.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
+
+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.
+
+<!-- end -->
Author	SHA1	Message	Date
Michael Radermacher	faf206fb66	auto-patch README.md	2024-05-14 15:38:49 +00:00
Michael Radermacher	a5dfb4a1bc	uploaded from nethype/db2	2024-05-14 15:32:37 +00:00
Michael Radermacher	144c0fbf21	uploaded from nethype/db2	2024-05-14 15:28:14 +00:00
Michael Radermacher	6d09e01995	uploaded from nethype/db2	2024-05-14 15:24:30 +00:00
Michael Radermacher	1fafc301a5	uploaded from nethype/db2	2024-05-14 15:23:20 +00:00
Michael Radermacher	5b153790d6	uploaded from nethype/db2	2024-05-14 15:22:01 +00:00
Michael Radermacher	b457d426e5	uploaded from nethype/db2	2024-05-14 15:20:46 +00:00
Michael Radermacher	c285bd1a10	uploaded from nethype/db2	2024-05-14 15:20:40 +00:00
Michael Radermacher	530a8fc22c	uploaded from nethype/db2	2024-05-14 15:19:49 +00:00
Michael Radermacher	cc4bf82fcb	uploaded from nethype/db2	2024-05-14 15:19:33 +00:00