Superduper allows users to work with self-hosted LLM models via [Llama.cpp](https://github.com/ggerganov/llama.cpp).
Project description
superduper_llamacpp
Superduper allows users to work with self-hosted LLM models via Llama.cpp.
Installation
pip install superduper_llamacpp
API
Class | Description |
---|---|
superduper_llamacpp.model.LlamaCpp |
Llama.cpp connector. |
superduper_llamacpp.model.LlamaCppEmbedding |
Llama.cpp connector for embeddings. |
Examples
LlamaCpp
from superduper_llama_cpp.model import LlamaCpp
model = LlamaCpp(
identifier="llm",
model_name_or_path="mistral-7b-instruct-v0.2.Q4_K_M.gguf",
)
model.predict("Hello world")
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file superduper_llamacpp-0.4.0.tar.gz
.
File metadata
- Download URL: superduper_llamacpp-0.4.0.tar.gz
- Upload date:
- Size: 11.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2b97f29cf76bebd9d5a9b0af6316cf471c387537d4eec6c275e7000af34332e5 |
|
MD5 | 6bbeeb223ae315bdc44ba01886dce56c |
|
BLAKE2b-256 | ba74c09159cfccc2d35e22b3f7e811b099a5a9528ee8207a483adb10bb0ecb45 |
Provenance
The following attestation bundles were made for superduper_llamacpp-0.4.0.tar.gz
:
Publisher:
release_plugins.yaml
on superduper-io/superduper
-
Statement type:
https://in-toto.io/Statement/v1
- Predicate type:
https://docs.pypi.org/attestations/publish/v1
- Subject name:
superduper_llamacpp-0.4.0.tar.gz
- Subject digest:
2b97f29cf76bebd9d5a9b0af6316cf471c387537d4eec6c275e7000af34332e5
- Sigstore transparency entry: 146081697
- Sigstore integration time:
- Predicate type:
File details
Details for the file superduper_llamacpp-0.4.0-py3-none-any.whl
.
File metadata
- Download URL: superduper_llamacpp-0.4.0-py3-none-any.whl
- Upload date:
- Size: 11.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 442950347ce25ded4f8987fb75635e2cb489dc42f65fd3fe71168155e3a8fd36 |
|
MD5 | 8e495b82d1fc0d12f912510a553ec459 |
|
BLAKE2b-256 | 7ce1541be885dee2257aa30da081afc45a522af2b4ececdbe201f68567dc6c76 |
Provenance
The following attestation bundles were made for superduper_llamacpp-0.4.0-py3-none-any.whl
:
Publisher:
release_plugins.yaml
on superduper-io/superduper
-
Statement type:
https://in-toto.io/Statement/v1
- Predicate type:
https://docs.pypi.org/attestations/publish/v1
- Subject name:
superduper_llamacpp-0.4.0-py3-none-any.whl
- Subject digest:
442950347ce25ded4f8987fb75635e2cb489dc42f65fd3fe71168155e3a8fd36
- Sigstore transparency entry: 146081698
- Sigstore integration time:
- Predicate type: