You can deploy this model and start earning money today!

RichardErkhov/
SpectraSuite_-_QuantLM_830M_8bit_Unpacked-exl2

Name: SpectraSuite_-_QuantLM_830M_8bit_Unpacked-exl2
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

QuantLM_830M_8bit_Unpacked - EXL2

Model creator: https://huggingface.co/SpectraSuite/
Original model: https://huggingface.co/SpectraSuite/QuantLM_830M_8bit_Unpacked/

Available sizes

| 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. |

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/SpectraSuite_-_QuantLM_830M_8bit_Unpacked-exl2 QuantLM_830M_8bit_Unpacked-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 SpectraSuite_-_QuantLM_830M_8bit_Unpacked-exl2 --revision 6_5 --local-dir QuantLM_830M_8bit_Unpacked-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download SpectraSuite_-_QuantLM_830M_8bit_Unpacked-exl2 --revision 6_5 --local-dir QuantLM_830M_8bit_Unpacked-6.5 --local-dir-use-symlinks False

Original model description:

license: apache-2.0

QuantLM 830M 8 bit

QuantLM, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLM has the same architecture as LLaMa.

python

import transformers as tf, torch
model_name = "SpectraSuite/QuantLM_830M_8bit_Unpacked"
# Please adjust the temperature, repetition penalty, top_k, top_p and other sampling parameters according to your needs.
pipeline = tf.pipeline("text-generation", model=model_id, model_kwargs={"torch_dtype": torch.float16}, device_map="auto")
# These are base (pretrained) LLMs that are not instruction and chat tuned. You may need to adjust your prompt accordingly.
pipeline("Once upon a time")

License: Apache 2.0
We will use our GitHub repo for communication (including HF repo related queries). Feel free to open an issue here https://github.com/NolanoOrg/SpectraSuite

RichardErkhov/SpectraSuite_-_QuantLM_830M_8bit_Unpacked-exl2