🦙 Llama Trainer Utility
A "just few lines of code" utility for fine-tuning (not only) Llama models.
To install:
pip install llama-trainer
Training and Inference
Training
from llama_trainer import LlamaTrainer
from datasets import load_dataset
dataset = load_dataset("timdettmers/openassistant-guanaco")
# define your instruction-based sample
def to_instruction_fn(sample):
return sample["text"]
formatting_func = to_instruction_fn
output_dir = "llama-2-7b-hf-finetune"
llama_trainer = LlamaTrainer(
model_name="meta-llama/Llama-2-7b-hf",
dataset=dataset,
formatting_func=formatting_func,
output_dir=output_dir
)
llama_trainer.train()
Inference
from llama_trainer import LlamaInfer
import transformers as tr
llama_infer = LlamaInfer(output_dir)
prompt = "### Human: Give me some output!### Assistant:"
print(llama_infer(prompt))
Metadata
Release files for llama-trainer 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llama-trainer-0.2.1.tar.gz | 11.7 kB | Without provenance | Details for llama-trainer-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llama_trainer-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for llama_trainer-0.2.1-py3-none-any.whl |
Total release size: 23.2 kB
Release files / llama-trainer-0.2.1.tar.gz
| Download URL | llama-trainer-0.2.1.tar.gz |
|---|---|
| Size | 11.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
54ff7bac916315161c75549f11043cbc70a016afaac207d7163a24f7f8f820a8
|
|
BLAKE2b-256 checksum How to use checksums |
2baf3b04b223e875ffbe748d8fbc4c54ab1f16abc5ead1d68c86306286d75507
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.18
|
Release files / llama_trainer-0.2.1-py3-none-any.whl
| Download URL | llama_trainer-0.2.1-py3-none-any.whl |
|---|---|
| Size | 11.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
03caffce8f476cbdea06f280e7a84fc55bc037b3489cce1ff3184a285b64afea
|
|
BLAKE2b-256 checksum How to use checksums |
a13ab5ff93529be225059ad789d74233d973bf2bb631565a19b258c8190a3175
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.18
|
Security for llama-trainer 0.2.1
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.