mradermacher/Blue-Orchid-2x7b-i1-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Compare commits

base: mradermacher:997f0444a3e973cc3df6a0df3a3c65fcee319eab
Branches Tags
mradermacher:main
...
compare: mradermacher:c7dedfc698c3bcf2da87373bf6c28b3da2f9ae71
Branches Tags
mradermacher:main

10 Commits
997f0444a3 ... c7dedfc698

Author SHA1 Message Date
Michael Radermacher
c7dedfc698 auto-patch README.md 2024-08-02 10:03:35 +00:00
Michael Radermacher
3a5f953d35 auto-patch README.md 2024-06-30 11:39:58 +00:00
Michael Radermacher
7498ccb121 uploaded from nethype/db2 2024-06-30 10:57:20 +00:00
Michael Radermacher
9123de5cba uploaded from nethype/db2 2024-06-30 10:53:13 +00:00
Michael Radermacher
7f35dbb2d9 uploaded from nethype/db2 2024-06-30 10:39:50 +00:00
Michael Radermacher
c0d5504356 uploaded from nethype/db2 2024-06-30 10:23:39 +00:00
Michael Radermacher
cb1de63a4f uploaded from nethype/db2 2024-06-30 10:07:13 +00:00
Michael Radermacher
415f6ea87f uploaded from nethype/db2 2024-06-30 09:59:44 +00:00
Michael Radermacher
1914ad9952 uploaded from nethype/db2 2024-06-30 09:53:16 +00:00
Michael Radermacher
388335853b uploaded from nethype/db2 2024-06-30 09:46:47 +00:00
10 changed files with 99 additions and 0 deletions
Expand all files Collapse all files

8
.gitattributes vendored
View File

@@ -47,3 +47,11 @@ Blue-Orchid-2x7b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
Blue-Orchid-2x7b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text

3
Blue-Orchid-2x7b.i1-IQ1_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf04ebc93828c5d3ec86b32880e8d1f22e15fd9c3b86c031b7a6a0b871ca25f9
size 3014313824

3
Blue-Orchid-2x7b.i1-IQ1_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:82459756b06197c2d6d6af220aecf56ee0f5ff297e9a74c8714525b6a198f67a
size 2745354080

3
Blue-Orchid-2x7b.i1-IQ2_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e7b9b734a9be7b1c0858d73b0c47212867b838e9e2f18a6ff3af27eb17e36518
size 3974489952

3
Blue-Orchid-2x7b.i1-IQ2_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:337471202b14e9728c7bb34c8e2c06fffd36e9ab31ec69b58fac0412ac9be936
size 3837970272

3
Blue-Orchid-2x7b.i1-IQ2_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5a27596bf1bd5c285d58226099940ebb8af67a2a18661365154dc76683074c3b
size 3462580064

3
Blue-Orchid-2x7b.i1-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a63cf9c8a4c335b6dfc28e1abd9a944b36c5328297b2f85748d91f74ed9c1f30
size 5739349856

3
Blue-Orchid-2x7b.i1-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c89362c473a4c5aac9fab551b986ad3c307ef538cc0385c079809d62b855191
size 5605656416

3
Blue-Orchid-2x7b.i1-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b73d80df495508d397d968258b0e2e2b2f12a7efb01158b730811cb94f03ebfa
size 5309957984

67
README.md
View File

@@ -1,6 +1,73 @@
---
base_model: nakodanei/Blue-Orchid-2x7b
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/nakodanei/Blue-Orchid-2x7b
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Blue-Orchid-2x7b-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/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.8 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ1_M.gguf) | i1-IQ1_M | 3.1 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ2_S.gguf) | i1-IQ2_S | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ2_M.gguf) | i1-IQ2_M | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.7 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.3 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q4_0.gguf) | i1-Q4_0 | 7.4 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.0 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.2 | |
| [GGUF](https://huggingface.co/mradermacher/Blue-Orchid-2x7b-i1-GGUF/resolve/main/Blue-Orchid-2x7b.i1-Q6_K.gguf) | i1-Q6_K | 10.7 | 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 -->