API
Added inference parameters customization and versatile API key choice
- Now you can configure inference parameters comparable to temperature, max tokens, and extra, relying on the particular mannequin you might be utilizing, for each text-to-text and text-to-image generative duties. This empowers you to customise and fine-tune your mannequin interactions to raised fit your particular person wants.
Bug Fixes
- Fastened a difficulty the place the ListWorkflows endpoint fetched workflows from deleted apps. Beforehand, workflows from deleted purposes had been fetched within the response of the ListWorkflows endpoint. We fastened the difficulty.
Python SDK
Added inference parameters customization and versatile API key choice
- The SDK helps the next textual content knowledge codecs: plain textual content, CSV, and TSV (in roadmap).
- It helps the next picture knowledge codecs: JPEG, PNG, TIFF, BMP, WEBP, and GIF.
- You’ve gotten the flexibleness to add knowledge from both URLs or native storage, whether or not it is inside a single folder or unfold throughout a number of sub-folders.
- You’ll be able to add textual content knowledge enriched with metadata and textual content classification annotations.
- You too can add picture knowledge enriched with annotations, geoinformation, and metadata data.
- You’ll be able to effectively create apps designed for textual content mode and picture mode use instances.
- The SDK ensures clear progress monitoring throughout every add and promptly stories any encountered errors.
Built-in YAML workflow interfaces with proto endpoints
- Within the SDK, the workflow interfaces are actually represented in YAML format, however they’re seamlessly built-in with proto endpoints for environment friendly communication and interplay.
Enhanced the SDK’s foundational construction
- The SDK now helps authentication solely utilizing Private Entry Tokens (PAT) and UserIDs.
- We plan to offer helper utilities for wealthy textual content formatting and printing to facilitate a user-friendly interplay.
- We’re working to always add a sturdy error-handling system that covers numerous eventualities.
New Revealed Fashions
Revealed a number of new, ground-breaking fashions
- Wrapped Falcon-40B-Instruct, a causal decoder-only Giant Language Mannequin (LLM) constructed by TII primarily based on Falcon-40B and fine-tuned on a mix of Baize.
- Wrapped WizardLM-70B, a mannequin fine-tuned on the Llama2-70B mannequin utilizing Evol+ strategies; it delivers excellent efficiency.
- Wrapped CodeLlama-13B-Instruct-GPTQ, CodeLlama-34B-Instruct-GPTQ, and CodeLlama-7B-GPTQ. Code Llama is a household of code-focused LLMs, constructed upon Llama 2. These fashions excel at filling in code, dealing with in depth enter contexts, and following programming directions with out prior coaching for numerous programming duties.
- Wrapped WizardLM-13B, an LLM fine-tuned on the Llama-2-13b mannequin utilizing the Evol+ method; it delivers excellent efficiency.
- Wrapped WizardCoder-15B, a code-based LLM that has been fine-tuned on Llama 2 utilizing the Evol-Instruct technique and has demonstrated superior efficiency in comparison with different open-source and closed-source LLMs on distinguished code technology benchmarks.
- Wrapped WizardCoder-Python-34B, a code-based LLM that has been fine-tuned on Llama 2. It excels in Python code technology duties and has demonstrated superior efficiency in comparison with different open-source and closed-source LLMs on distinguished code technology benchmarks.
- Wrapped Phi-1, a high-performing 1.3 billion-parameter text-to-code language mannequin, excelling in Python code technology duties whereas prioritizing high-quality coaching knowledge.
- Wrapped Phi-1.5, a 1.3 billion parameter LLM that excels at advanced reasoning duties and was educated on a high-quality artificial dataset.
- Wrapped OpenAI’s GPT-3.5-Turbo-Instruct, an LLM designed to excel in understanding and executing particular directions effectively. It excels at finishing duties and offering direct solutions to questions.
- Wrapped Mistral-7B-Instruct, a state-of-the-art 7.3 billion parameter language mannequin, outperforming Llama2-13B in a number of NLP benchmarks, together with code-related challenges.
LlamaIndex
We now assist integrating with the LlamaIndex knowledge framework for numerous use instances, together with:
- Ingesting, structuring, and accessing exterior knowledge for the LLMs you fine-tune on our platform. This lets you increase the accuracy of your LLM purposes with non-public or domain-specific knowledge.
- Storing and indexing your knowledge for numerous functions, together with integrating with our downstream vector search and database providers.
- Constructing an embeddings question interface that accepts any enter immediate and leverages your knowledge to offer knowledge-augmented responses.
Fashions
Added means to fine-tune text-to-text fashions
- Superior mannequin builders can now additional customise the habits and output of the text-to-text fashions for particular textual content technology duties. They’ll practice the fashions on particular datasets to adapt their habits for specific duties or domains.
[Enterprise Preview] Fastened a difficulty with the Leaderboard, which organizes fashions primarily based on their analysis outcomes
- Beforehand, for visible detection fashions, the displayed metrics included classification metrics like ROC, as a substitute of the anticipated metric, which is Imply Common Precision (MAP). The Leaderboard now accurately shows MAP, identical to within the mannequin viewer’s model desk.
Bug Fixes
- Launched multi-label textual content classification with Hugging Face textual content classification pipeline. Beforehand, there was a difficulty with multi-label textual content classification utilizing the Hugging Face textual content classification pipeline. Whereas it labored nicely for multi-class classification, it didn’t carry out accurately for multi-label classification. We fastened the difficulty.
- Fastened points with the mannequin model particulars web page.
- Fastened a difficulty that prevented the mannequin model particulars web page from displaying any output fields.
- Fastened a difficulty that induced the mannequin model particulars desk web page to crash unexpectedly.
- Fastened a difficulty the place the mannequin model particulars web page displayed incorrect parameter values when switching between totally different mannequin variations.
- Fastened a difficulty the place the mannequin model particulars web page displayed fields irrelevant to the particular mannequin kind. Pointless fields unrelated to the chosen mannequin kind are actually not seen.
- Fastened a difficulty the place the Mannequin Viewer web page incorrectly rotated photos in particular group apps. Beforehand, when photos with a portrait orientation (top larger than width) had been submitted to some apps, the expected detection bins appeared misaligned or incorrect. The Mannequin Viewer web page now accurately rotates photos with portrait orientation, aligning detection bins precisely for improved person expertise and detection accuracy.
- Fastened a difficulty the place the mannequin ID disappeared after deciding on the Base embed_model within the mannequin creation course of. Beforehand, customers encountered a difficulty the place their beforehand entered mannequin ID would disappear upon deciding on a base embed mannequin when creating a brand new mannequin. We fastened the difficulty.
Modules
Eliminated collaborative purposes from the apps drop-down checklist throughout the Set up Module modal when an org person is chosen
- Since group customers should not have collaborative apps or interact in collaborations, we’ve got optimized the interface by eradicating collaborated apps within the Set up Module modal particularly for this person group. This additionally fastened the app failure bug.
Enhanced the default app choice within the Set up Module modal
- The Set up Module modal now routinely selects your present app because the default vacation spot to put in your chosen module.
Improved the search performance for modules
- This refinement within the search characteristic gives a extra streamlined and productive expertise when in search of particular modules or associated content material.
Launched a useful addition to the module’s viewer web page—an easy-to-use copy icon
- Now you can click on the copy icon situated within the Newest Model ID part to swiftly receive the whole newest model URL for a module. This URL lets you expedite the module set up course of on your utility.
Enter-Supervisor
Added means to view and tag textual content inputs throughout the Enter-Viewer
- We now have designed a complete UI that lets you interactively create and handle annotations for textual content inputs.
Bug Fixes
- Improved keyboard shortcut performance in Enter-Viewer. Within the Enter-Viewer, you need to use keyboard shortcuts (hotkeys), comparable to H, V, P, and B, to modify between annotation instruments.
- Beforehand, when opening the mannequin selector or every other factor with a popover whereas within the Enter-Viewer, typing any of the hotkeys would unintentionally change instruments within the background. We fastened the difficulty, and the hotkeys don’t now set off occasions that have an effect on instruments within the background.
- Enabled error-free transition to annotation mode in Enter-Viewer. Beforehand, there was an error instantly after switching to annotation mode within the Enter-Viewer. We fastened the difficulty.
- Fastened concern stopping collaborators from creating annotations in Enter-Viewer. Collaborators can now actively take part within the annotation course of, contributing to a extra collaborative and environment friendly workflow.
- Improved the Enter-Viewer’s URL dealing with to make sure a extra seamless navigation expertise. Beforehand, there was a difficulty the place the enter ID a part of the route parameters was not utilized successfully for rendering, resulting in undesired redirects. We fastened the difficulty.
Invites
- Now you can seamlessly assessment and settle for pending Group invites instantly throughout the Portal, eliminating the necessity to rely solely on electronic mail for this function. That is worthwhile for each our SaaS providing and our on-premise deployments, because it caters to eventualities the place electronic mail assist could also be restricted or unavailable.
Group Settings and Administration
Bug Fixes
- Fastened a difficulty with displaying incorrect menu gadgets within the cellular view. Beforehand, whenever you switched out of your private person account to a corporation account by clicking your profile icon on the top-right nook of the navigation menu bar, the drop-down checklist displayed your private particulars as a substitute of the group’s data. We fastened the difficulty.
- Fastened a difficulty the place a corporation contributor couldn’t entry public workflows. Group contributors (group members) can now fetch an entire checklist of all public workflows with none hindrances.
- Enabled group contributors to view obtainable vacation spot apps in Set up Module Modal. We fastened a difficulty that beforehand hindered group contributors from viewing the checklist of obtainable vacation spot apps throughout the Set up Module modal when making an attempt to put in a module.
- Fastened a difficulty with trying to find group members. Beforehand, whenever you used a number of parameters, comparable to each first title and final title collectively, to seek for members whose first title or final title matched the question textual content, it may end in an error throughout the response. We fastened the difficulty.
- Fastened a difficulty the place collaborators with the group contributor function didn’t checklist mannequin evaluations. Beforehand, collaborators attempting to checklist mannequin evaluations encountered an error message stating “Inadequate scopes”, regardless of the expectation that the function would grant them entry to view evaluations. We fastened the difficulty.
Apps
Enhanced App Settings web page to show particulars of collaborators
- Now, you’ll be able to simply entry and examine the small print of your collaborators, together with their ID, first and final title, electronic mail, job function, and the date they had been added to the app.
Bug Fixes
- Fastened a difficulty the place the app thumbnails weren’t cached correctly. Beforehand, there was a difficulty the place the photographs of uploaded app thumbnails on the App Overview web page and on the drop-down sidebar checklist, which supplies fast entry to your obtainable apps, often appeared as clean or lacking. We fastened the difficulty.
Login/Logout and Signup Stream
Launched modal pop-ups for login and signup, and for numerous eventualities the place redirects had been beforehand employed
- We now have retained devoted login and signup pages whereas introducing modal home windows for these actions. Now you can entry login and signup capabilities instantly out of your energetic web page, offering fast and quick access to those important options.
- For operations like “Use Mannequin,” “Use Workflow,” “Set up Modules,” and extra, we’ve got changed the redirection course of with modal pop-ups. This eliminates the additional step and ensures a smoother person journey.
Bug Fixes
- Fastened a difficulty with the reCAPTCHA system. We improved the reCAPTCHA system to supply customers a notably smoother and extra user-friendly expertise.
Labeling Duties
Bug Fixes
- Fastened a difficulty the place it was not doable to submit labeled inputs for some labeling duties. Beforehand, you may not submit labeled inputs for sure labeled duties. When engaged on some labeling duties, if you happen to loaded the enter, chosen the related ideas, and tried to submit your labeled enter, you may encounter an error. We fastened the difficulty.
Workflows
Bug Fixes
- Fastened a difficulty with processing movies utilizing the Common workflow. Now you can confidently course of movies with the Common workflow with out encountering any hindrances or points.
- Fastened a difficulty with enhancing a workflow. Beforehand, whereas enhancing any workflow, the mannequin model displayed “No outcomes discovered,” which was inconsistent with the preliminary workflow creation expertise. The mannequin model habits now matches what’s displayed when initially making a workflow.
- Fastened a difficulty the place it was not doable to repeat a workflow with out first altering its ID. Beforehand, you may efficiently copy a workflow solely after altering the copied workflow ID. Now you can copy an present workflow, even if you happen to maintain the identical workflow title in the course of the copying course of, comparable to from “(workflow title)-copy” to “(workflow title)-copy.”
- Eliminated the default/base workflow from “Use Mannequin” modal. To make use of a mannequin in a workflow, go to the mannequin’s viewer web page, click on the “Use Mannequin” button on the upper-right nook of the web page, choose the “Use in a Workflow” tab, and choose a vacation spot app and its base workflow. You’ll be redirected to the workflow editor web page.
- Beforehand, if you happen to tried to replace the workflow within the editor web page, you may encounter an error. The difficulty arises as a result of the app’s default/base workflow can’t be edited, however this limitation is communicated to the person late solely after they’ve made modifications to the workflow. We fastened the difficulty by graying out or excluding the bottom workflow choice when customers try to make use of a mannequin in an present base workflow.
Markdown Search
Added means to carry out text-based searches throughout the markdown notes of apps, fashions, workflows, modules, and datasets
- For example, whenever you go to https://clarifai.com/discover/fashions and enter “detecting the presence” within the search subject, the outcomes will embrace any related useful resource the place the phrase “detecting the presence” is discovered throughout the markdown notes. This characteristic enhances search performance and permits for extra exact and context-aware discovery of assets primarily based on the content material inside their markdown notes.
Cowl Picture
Added cowl picture assist for numerous sorts of assets, together with apps, datasets, fashions, workflows, and modules
- This characteristic provides a visually partaking factor to your assets, making them extra interesting and informative. You too can delete the picture if you wish to.
