SpectraSuite_-_FloatLM_830M-exl2

Quantization made by Richard Erkhov.

Github

Discord

Request more models

FloatLM_830M - EXL2

• Model creator: https://huggingface.co/SpectraSuite/
• Original model: https://huggingface.co/SpectraSuite/FloatLM_830M/

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_-_FloatLM_830M-exl2 FloatLM_830M-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_-_FloatLM_830M-exl2 --revision 6_5 --local-dir FloatLM_830M-6_5 --local-dir-use-symlinks False

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

huggingface-cli download SpectraSuite_-_FloatLM_830M-exl2 --revision 6_5 --local-dir FloatLM_830M-6.5 --local-dir-use-symlinks False

Original model description:

license: apache-2.0

FloatLM 830M

The good ol' FP16 LLMs with LLaMa architecture.

import transformers as tf, torch
model_name = "SpectraSuite/FloatLM_830M"

# 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