Metadata-Version: 2.4
Name: clyxbox
Version: 0.3.2
Summary: Inference runtime for Clyx causal language models
Author: Syntropic
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/PavBss/LM
Project-URL: Repository, https://github.com/PavBss/LM
Project-URL: Issues, https://github.com/PavBss/LM/issues
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: torch>=2.0.0
Requires-Dist: transformers>=4.30.0
Requires-Dist: huggingface-hub>=0.20.0
Requires-Dist: safetensors>=0.4.0
Requires-Dist: fastapi>=0.100.0
Requires-Dist: uvicorn>=0.23.0

# ClyxBox

Inference runtime for Clyx causal language models.

```bash
pip install clyxbox==0.3.2
```

```python
from clyxbox import ClyxPipeline

pipe = ClyxPipeline.from_pretrained(
    "syntropic-clx/Clyx_0.3-635.51M-BASE",
    device="cuda",
)
text = pipe("Once upon a time", max_new_tokens=128, stream=True)
```

When `dtype` is omitted, ClyxBox selects native BF16 on supported CUDA GPUs
(for example, A100) and FP32 otherwise (including T4). Pass `dtype="float16"`
or `dtype="bfloat16"` only when you have verified that precision on your GPU.

The default sampling settings are `temperature=0.65`, `top_p=0.90`,
`top_k=50`, and `repetition_penalty=1.12`. Sampling is stochastic, so
outputs can differ between runs. A BASE checkpoint continues text and may
produce repetitive or off-topic continuations; these settings cannot turn it
into an instruction-following assistant.

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.
