TinkerThinking Machines Lab
|
||||||
Related Products
|
||||||
About
A single line of code to supercharge your LLM with integrations and without complex JSON schemas. Spend minutes, not days adding integrations to your LLM. With only a few lines of code, the LLM can perform any action in any target app on behalf of the user. 2,200 out-of-the-box integrations. Connect with Google Calendar, Gmail, Hubspot, Salesforce or more. Manage authentication profiles so your LLM can perform actions on behalf of your users. Build REST integrations or easily import from a OpenAPI spec. Function calling requires the foundation model to be fine-tuned which can be expensive and diminish the quality of your output. Enable function calling with any LLM, even if it's not natively supported. With Astra, you can build a seamless layer of integrations and function execution on top of your LLM, extending its capabilities without altering its core structure. Automatically generate LLM-optimized field descriptions.
|
About
Tinker is a training API designed for researchers and developers that allows full control over model fine-tuning while abstracting away the infrastructure complexity. It supports primitives and enables users to build custom training loops, supervision logic, and reinforcement learning flows. It currently supports LoRA fine-tuning on open-weight models across both LLama and Qwen families, ranging from small models to large mixture-of-experts architectures. Users write Python code to handle data, loss functions, and algorithmic logic; Tinker handles scheduling, resource allocation, distributed training, and failure recovery behind the scenes. The service lets users download model weights at different checkpoints and doesn’t force them to manage the compute environment. Tinker is delivered as a managed offering; training jobs run on Thinking Machines’ internal GPU infrastructure, freeing users from cluster orchestration.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Professional users wanting a tool to integrate any app and API with an LLM for function calling
|
Audience
AI researchers and ML engineers requiring a solution to experiment with fine-tuning open source language models while outsourcing infrastructure complexity
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationAstra Platform
www.tryastra.io
|
Company InformationThinking Machines Lab
United States
thinkingmachines.ai/tinker/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Gmail
Google Calendar
HubSpot CRM
HubSpot Customer Platform
Inkling
Inkling-Small
JSON
Jira
Llama 3
Llama 3.1
|
Integrations
Gmail
Google Calendar
HubSpot CRM
HubSpot Customer Platform
Inkling
Inkling-Small
JSON
Jira
Llama 3
Llama 3.1
|
|||||
|
|
|