|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
license: llama2 |
|
quantized_by: mradermacher |
|
--- |
|
## About |
|
|
|
Weighted imatrix quantize of https://huggingface.co/sophosympatheia/Midnight-Rose-103B-v2.0.3 |
|
|
|
The weight was calculated using an experimental (potentially crappy) method that is iterative (thus the "i1"), using 270k semi-random english tokens. |
|
<!-- 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/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ1_S.gguf) | i1-IQ1_S | 22.0 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.6 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.7 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q2_K.gguf) | i1-Q2_K | 38.2 | | |
|
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 40.5 | fast, lower quality | |
|
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 42.3 | IQ3-XXS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 44.8 | IQ3-XXS probably better | |
|
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-ab) | i1-Q3_K_M | 49.9 | lower quality | |
|
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 54.4 | | |
|
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 58.9 | fast, medium quality | |
|
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 62.2 | fast, medium quality | |
|
|
|
|
|
Here is a handy table comparing some lower-quality quant types: |
|
|
|
 |
|
|
|
<!-- end --> |
|
|
