Commit
•
054a2ef
1
Parent(s):
563a3d9
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1 +1,47 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
library_name: transformers
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
quantized_by: mradermacher
|
| 7 |
+
---
|
| 8 |
+
## About
|
| 9 |
+
|
| 10 |
+
weighted/imatrix wuants of https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
|
| 11 |
+
<!-- provided-files -->
|
| 12 |
+
|
| 13 |
+
## Usage
|
| 14 |
+
|
| 15 |
+
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
| 16 |
+
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
|
| 17 |
+
more details, including on how to concatenate multi-part files.
|
| 18 |
+
|
| 19 |
+
## Provided Quants
|
| 20 |
+
|
| 21 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 22 |
+
|
| 23 |
+
| Link | Type | Size/GB | Notes |
|
| 24 |
+
|:-----|:-----|--------:|:------|
|
| 25 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 9.7 | |
|
| 26 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.5 | |
|
| 27 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 13.8 | |
|
| 28 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 17.5 | IQ3_XXS probably better |
|
| 29 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.5 | fast, lower quality |
|
| 30 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 19.2 | |
|
| 31 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.6 | IQ3_XS probably better |
|
| 32 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.7 | IQ3_S probably better |
|
| 33 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
|
| 34 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.9 | almost as good as Q4_K_M |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.6 | fast, medium quality |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Instruct-v0.1-i1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.4 | best weighted quant |
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 40 |
+
types (lower is better):
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
And here are Artefact2's thoughts on the matter:
|
| 45 |
+
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
| 46 |
+
|
| 47 |
+
<!-- end -->
|