mradermacher's picture
auto-patch README.md
73728fc verified
|
raw
history blame
2.88 kB
---
datasets:
- ehartford/samantha-data
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
---
## About
weighted/imatrix quants of https://huggingface.co/cognitivecomputations/Samantha-1.11-70b
<!-- provided-files -->
## 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/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.4 | fast, lower quality |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 28.7 | |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Samantha-1.11-70b-i1-GGUF/resolve/main/Samantha-1.11-70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, medium quality |
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
## 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 -->