ClyxBox
Inference runtime for Clyx causal language models.
pip install clyxbox
from clyxbox import ClyxPipeline
pipe = ClyxPipeline.from_pretrained(
"syntropic-clx/Clyx_0.3-635.51M-BASE",
device="cuda",
dtype="bfloat16",
)
text = pipe("Once upon a time", max_new_tokens=128, stream=True)
The package supports Hugging Face model repositories and Clyx inference bundles,
including exports split across multiple Safetensors files. For a sharded export,
keep model.safetensors.index.json and every referenced shard in the same
repository; ClyxModel.from_pretrained reads the index and loads each shard
automatically. A BASE checkpoint continues text; it is not automatically an
instruction-following assistant.
Release files for clyxbox 0.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| clyxbox-0.3.1.tar.gz | 10.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| clyxbox-0.3.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 22.7 kB
Release files / clyxbox-0.3.1.tar.gz
| Download URL | clyxbox-0.3.1.tar.gz |
|---|---|
| Size | 10.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4c0aca27fb5bb12ca4550cb2aa4d896adc13aa1d3172c8e7934d192b18db58ff
|
|
BLAKE2b-256 checksum How to use checksums |
8a9c3403ff448485c5fa59d2628d2f7116b46de58508f6fa56dcb5414bfdbd2e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.9
|
Release files / clyxbox-0.3.1-py3-none-any.whl
| Download URL | clyxbox-0.3.1-py3-none-any.whl |
|---|---|
| Size | 12.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6eb07df529ac201f4e7f9cfff700624ff04d741fcd508cbe5b8bde24fbe84fa1
|
|
BLAKE2b-256 checksum How to use checksums |
8acdc5f69caf3f1fe3359120314799e45ee2fcd77850a8f7d031d5f42565a4fd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.9
|