Downloads · 30 days
0
RichardErkhov/lordspline_-_qwen-merged-exl2
lordspline_-_qwen-merged-exl2 is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
0
Access
Public
Updated Jan 18, 2025
Repo size
5.2 GB
Likes
0
Public
Click a slice to open those files.
.json670 KB · 99%
From the Hugging Face model README
Quantization made by Richard Erkhov.
qwen-merged - EXL2
| Branch | Bits | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ | | 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. | | 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. | | 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. | | 3_5 | 3.5 | Lower quality, only use if you have to. |
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/lordspline_-_qwen-merged-exl2 qwen-merged-6_5
With huggingface hub:
pip3 install huggingface-hub
To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:
Linux:
huggingface-cli download lordspline_-_qwen-merged-exl2 --revision 6_5 --local-dir qwen-merged-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
huggingface-cli download lordspline_-_qwen-merged-exl2 --revision 6_5 --local-dir qwen-merged-6.5 --local-dir-use-symlinks False
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Qwen/Qwen2-1.5B-Instruct
layer_range: [0, 6]
- sources:
- model: Qwen/Qwen2-1.5B-Instruct
layer_range: [22, 28]
merge_method: passthrough
dtype: float16