Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Salesforce

xLAM-7b-r

xLAM-7b-r is a 7.24B-parameter Mistral text-generation model from Salesforce. According to the model card, it targets general tool use and function calling.

Publisher
Salesforce
Task
text-generation
Model type
mistral
License
cc-by-nc-4.0
Library
transformers
Publication status
Approved for indexing

Model overview

xLAM-7b-r is published by Salesforce as a text-generation model. The captured configuration identifies MistralForCausalLM, and Safetensors metadata reports 7,241,732,096 parameters. According to the model card, it belongs to the general tool-use xLAM series with function-calling support.

Recorded capabilities

General tool-use positioning

Captured hub tags record function-calling, tool-use, and LLM Agent use, and the model card places this repository in the general tool-use series.

Publisher-listed series context

According to the model card, the xLAM series spans 1.35B to 141B variants, with xLAM-7b-r listed at 7.24B, 32k context, and a Sep. 5, 2024 release.

Prompt-format-dependent JSON calls

According to the model card, the publisher recommends its own prompt format and helpers to extract JSON tool_calls output in a ChatGPT-like function-calling mode.

Publisher-cited leaderboard context

According to the model card, the publisher references the Berkeley Function-Calling Leaderboard v2 with a Sep. 3, 2024 cutoff; no scores were extracted from the captured evidence.

Use cases in the source record

  • Agent and tool-use workflows that emit JSON function calls through the publisher's documented prompt format.
  • Multi-turn API-request experiments using the card's task, format, and history instructions with chat-template generation.

Limitations and unknowns

  • No evaluation results were extracted from this record as structured data; the card's leaderboard reference includes no scores in the captured evidence.
  • The 32k context length and Sep. 5, 2024 release date are publisher-table statements, not independently verified measurements.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Salesforce/xLAM-7b-r

Captured: Unknown. Processed: 2026-09-07T19:34:36.405240+00:00.

[Homepage] | [Paper] | [Github] | [Discord] | [Blog] | [Community Demo] Welcome to the xLAM model family! Large Action Models (LAMs) are advanced large language models designed to enhance decision-making and translate user intentions into executable actions that interact with the world. LAMs autonomously plan and execute tasks to achieve specific goals, serving as the brains of AI agents. They have the potential to automate workflow processes across various domains, making them invaluable for a wide range of applications. The model release is exclusively for research purposes. A new and enhanced version of xLAM will soon be availabl…

F001F002F003F004F005F006F007F009F010F013F014F016F017F018F019F029F034F042