ptblop
Package containing builders for block-pruned transformer models in PyTorch.
Installation
You can install ptblop package via pip:
pip install ptblop
Creating a block-pruned model
To create a block-pruned model, you need a bp_config usually serialized in a
JSON file. A code sample for loading block pruned language model Qwen/Qwen1.5-4B
from transformers library is included below. Sample bp_configs for Qwen/Qwen1.5-4B
are here.
import json
import ptblop
import transformers
import torch
bp_config_path = "./bp_config.json"
model_name = "Qwen/Qwen1.5-4B"
dtype = torch.bfloat16
model = transformers.AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=dtype,
trust_remote_code=True,
)
with open(bp_config_path, "rt") as f:
bp_config = json.load(f)
ptblop.apply_bp_config_in_place(model, bp_config)
1 maintainer
Metadata
1 maintainer
Release files for ptblop 0.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ptblop-0.4.0.tar.gz | 15.3 kB | Without provenance | Details for ptblop-0.4.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ptblop-0.4.0-py3-none-any.whl | Python 3 | none | any | Details for ptblop-0.4.0-py3-none-any.whl |
Total release size: 37.4 kB
Release files / ptblop-0.4.0.tar.gz
| Download URL | ptblop-0.4.0.tar.gz |
|---|---|
| Size | 15.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c7207252a73ab2d1463b7fd84503e9f271efc1a0d434b2ce0902a41e2f0923b8
|
|
BLAKE2b-256 checksum How to use checksums |
226190d65ba5782af214dd668744396e563d27a27fb5cb0ad2bec078ae310481
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.10
|
Release files / ptblop-0.4.0-py3-none-any.whl
| Download URL | ptblop-0.4.0-py3-none-any.whl |
|---|---|
| Size | 22.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
baeeb89ea4be444a7f5276ffb17909cb349c9a64c21d12e8d6b41e1eba9eb545
|
|
BLAKE2b-256 checksum How to use checksums |
1f9548c9ab2b2f648d9b4b57c0da8a7936b1ac033f35334d132b343436c7c153
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.10
|
Security for ptblop 0.4.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
