| Name | wisent JSON |
| Version |
0.1.1
JSON |
| download |
| home_page | https://github.com/wisent-ai/wisent |
| Summary | Client library for interacting with the Wisent backend services |
| upload_time | 2025-03-03 00:11:52 |
| maintainer | None |
| docs_url | None |
| author | Wisent Team |
| requires_python | >=3.8 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Wisent
A Python client library for interacting with the Wisent backend services.
## Installation
```bash
pip install wisent
```
## Features
- **Activations**: Extract and send model activations to the Wisent backend
- **Control Vectors**: Retrieve and apply control vectors for model inference
- **Inference**: Utilities for applying control vectors during inference
- **Utilities**: Helper functions for common tasks
## Quick Start
```python
from wisent import WisentClient
# Initialize the client
client = WisentClient(api_key="your_api_key", base_url="https://api.wisent.ai")
# Extract activations from a model and send to backend
activations = client.activations.extract(
model_name="mistralai/Mistral-7B-Instruct-v0.1",
prompt="Tell me about quantum computing",
layers=[0, 12, 24]
)
# Get a control vector from the backend
control_vector = client.control_vector.get(
name="helpful",
model="mistralai/Mistral-7B-Instruct-v0.1"
)
# Apply a control vector during inference
response = client.inference.generate_with_control(
model_name="mistralai/Mistral-7B-Instruct-v0.1",
prompt="Tell me about quantum computing",
control_vectors={"helpful": 0.8, "concise": 0.5}
)
# Print the response
print(response.text)
```
## Advanced Usage
### Extracting Activations
```python
from wisent.activations import ActivationExtractor
# Create an extractor
extractor = ActivationExtractor(
model_name="mistralai/Mistral-7B-Instruct-v0.1",
device="cuda"
)
# Extract activations for a specific prompt
activations = extractor.extract(
prompt="Tell me about quantum computing",
layers=[0, 12, 24],
tokens_to_extract=[-10, -1] # Extract last 10 tokens and final token
)
# Send activations to the Wisent backend
from wisent import WisentClient
client = WisentClient(api_key="your_api_key")
client.activations.upload(activations)
```
### Working with Control Vectors
```python
from wisent.control_vector import ControlVectorManager
# Initialize the manager
manager = ControlVectorManager(api_key="your_api_key")
# Get a control vector
helpful_vector = manager.get("helpful", model="mistralai/Mistral-7B-Instruct-v0.1")
# Combine multiple vectors
combined_vector = manager.combine(
vectors={
"helpful": 0.8,
"concise": 0.5
},
model="mistralai/Mistral-7B-Instruct-v0.1"
)
# Apply during inference
from wisent.inference import Inferencer
inferencer = Inferencer(model_name="mistralai/Mistral-7B-Instruct-v0.1")
response = inferencer.generate(
prompt="Tell me about quantum computing",
control_vector=combined_vector,
method="caa" # Context-Aware Addition
)
```
## Documentation
For full documentation, visit [docs.wisent.ai](https://docs.wisent.ai).
## License
MIT
Raw data
{
"_id": null,
"home_page": "https://github.com/wisent-ai/wisent",
"name": "wisent",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": null,
"author": "Wisent Team",
"author_email": "info@wisent.ai",
"download_url": "https://files.pythonhosted.org/packages/6c/72/1a63f9c2e5fe2accd236b3ea18844e8f0d224353e72097cbddbef6a83409/wisent-0.1.1.tar.gz",
"platform": null,
"description": "# Wisent\n\nA Python client library for interacting with the Wisent backend services.\n\n## Installation\n\n```bash\npip install wisent\n```\n\n## Features\n\n- **Activations**: Extract and send model activations to the Wisent backend\n- **Control Vectors**: Retrieve and apply control vectors for model inference\n- **Inference**: Utilities for applying control vectors during inference\n- **Utilities**: Helper functions for common tasks\n\n## Quick Start\n\n```python\nfrom wisent import WisentClient\n\n# Initialize the client\nclient = WisentClient(api_key=\"your_api_key\", base_url=\"https://api.wisent.ai\")\n\n# Extract activations from a model and send to backend\nactivations = client.activations.extract(\n model_name=\"mistralai/Mistral-7B-Instruct-v0.1\",\n prompt=\"Tell me about quantum computing\",\n layers=[0, 12, 24]\n)\n\n# Get a control vector from the backend\ncontrol_vector = client.control_vector.get(\n name=\"helpful\",\n model=\"mistralai/Mistral-7B-Instruct-v0.1\"\n)\n\n# Apply a control vector during inference\nresponse = client.inference.generate_with_control(\n model_name=\"mistralai/Mistral-7B-Instruct-v0.1\",\n prompt=\"Tell me about quantum computing\",\n control_vectors={\"helpful\": 0.8, \"concise\": 0.5}\n)\n\n# Print the response\nprint(response.text)\n```\n\n## Advanced Usage\n\n### Extracting Activations\n\n```python\nfrom wisent.activations import ActivationExtractor\n\n# Create an extractor\nextractor = ActivationExtractor(\n model_name=\"mistralai/Mistral-7B-Instruct-v0.1\",\n device=\"cuda\"\n)\n\n# Extract activations for a specific prompt\nactivations = extractor.extract(\n prompt=\"Tell me about quantum computing\",\n layers=[0, 12, 24],\n tokens_to_extract=[-10, -1] # Extract last 10 tokens and final token\n)\n\n# Send activations to the Wisent backend\nfrom wisent import WisentClient\nclient = WisentClient(api_key=\"your_api_key\")\nclient.activations.upload(activations)\n```\n\n### Working with Control Vectors\n\n```python\nfrom wisent.control_vector import ControlVectorManager\n\n# Initialize the manager\nmanager = ControlVectorManager(api_key=\"your_api_key\")\n\n# Get a control vector\nhelpful_vector = manager.get(\"helpful\", model=\"mistralai/Mistral-7B-Instruct-v0.1\")\n\n# Combine multiple vectors\ncombined_vector = manager.combine(\n vectors={\n \"helpful\": 0.8,\n \"concise\": 0.5\n },\n model=\"mistralai/Mistral-7B-Instruct-v0.1\"\n)\n\n# Apply during inference\nfrom wisent.inference import Inferencer\ninferencer = Inferencer(model_name=\"mistralai/Mistral-7B-Instruct-v0.1\")\nresponse = inferencer.generate(\n prompt=\"Tell me about quantum computing\",\n control_vector=combined_vector,\n method=\"caa\" # Context-Aware Addition\n)\n```\n\n## Documentation\n\nFor full documentation, visit [docs.wisent.ai](https://docs.wisent.ai).\n\n## License\n\nMIT\n",
"bugtrack_url": null,
"license": null,
"summary": "Client library for interacting with the Wisent backend services",
"version": "0.1.1",
"project_urls": {
"Homepage": "https://github.com/wisent-ai/wisent"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "a7b1049d60092495f20a16f9cee3af6a9e19a007f93703e6b4d6bb7188d071de",
"md5": "29f713fef40eeb7f7de514aab0060229",
"sha256": "703697836d1f4706deeabef8044822f54b4344e4df0e30d12883ed3cd4ccbc9d"
},
"downloads": -1,
"filename": "wisent-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "29f713fef40eeb7f7de514aab0060229",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 19390,
"upload_time": "2025-03-03T00:11:48",
"upload_time_iso_8601": "2025-03-03T00:11:48.446155Z",
"url": "https://files.pythonhosted.org/packages/a7/b1/049d60092495f20a16f9cee3af6a9e19a007f93703e6b4d6bb7188d071de/wisent-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6c721a63f9c2e5fe2accd236b3ea18844e8f0d224353e72097cbddbef6a83409",
"md5": "df270fc04d1b74be0eaa3181cd66e1ec",
"sha256": "c0a8e4aff91476e81aba2b5a372cb6cddaca3347e2853a269ed87b1203f08198"
},
"downloads": -1,
"filename": "wisent-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "df270fc04d1b74be0eaa3181cd66e1ec",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 20575,
"upload_time": "2025-03-03T00:11:52",
"upload_time_iso_8601": "2025-03-03T00:11:52.173666Z",
"url": "https://files.pythonhosted.org/packages/6c/72/1a63f9c2e5fe2accd236b3ea18844e8f0d224353e72097cbddbef6a83409/wisent-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-03-03 00:11:52",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "wisent-ai",
"github_project": "wisent",
"github_not_found": true,
"lcname": "wisent"
}
