6 items tagged “llm-tool-use”
Tool use is when an LLM is instructed to occasionally request that an external tool be run on its behalf, with the result passed back to the model for further processing. Sometimes also known as function calling, and one of several ideas that might be referred to as "agents".
2024
Mistral NeMo. Released by Mistral today: "Our new best small model. A state-of-the-art 12B model with 128k context length, built in collaboration with NVIDIA, and released under the Apache 2.0 license."
Nice to see Mistral use Apache 2.0 for this, unlike their Codestral 22B release - though Codestral Mamba was Apache 2.0 as well.
Mistral's own benchmarks but NeMo slightly ahead of the smaller (but same general weight class) Gemma 2 9B and Llama 3 8B models.
It's both multi-lingual and trained for tool usage:
The model is designed for global, multilingual applications. It is trained on function calling, has a large context window, and is particularly strong in English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.
Part of this is down to the new Tekken tokenizer, which is 30% more efficient at representing both source code and most of the above listed languages.
You can try it out via Mistral's API using llm-mistral like this:
pipx install llm
llm install llm-mistral
llm keys set mistral
# paste La Plateforme API key here
llm mistral refresh # if you installed the plugin before
llm -m mistral/open-mistral-nemo 'Rave about pelicans in French'
Introducing Llama-3-Groq-Tool-Use Models (via) New from Groq: two custom fine-tuned Llama 3 models specifically designed for tool use. Hugging Face model links:
Groq's own internal benchmarks put their 70B model at the top of the Berkeley Function-Calling Leaderboard with a score of 90.76 (and 89.06 for their 8B model, which would put it at #3). For comparison, Claude 3.5 Sonnet scores 90.18 and GPT-4-0124 scores 88.29.
The two new Groq models are also available through their screamingly-fast (fastest in the business?) API, running at 330 tokens/s and 1050 tokens/s respectively.
Here's the documentation on how to use tools through their API.
llm-command-r. Cohere released Command R Plus today—an open weights (non commercial/research only) 104 billion parameter LLM, a big step up from their previous 35 billion Command R model.
Both models are fine-tuned for both tool use and RAG. The commercial API has features to expose this functionality, including a web-search connector which lets the model run web searches as part of answering the prompt and return documents and citations as part of the JSON response.
I released a new plugin for my LLM command line tool this morning adding support for the Command R models.
In addition to the two models it also adds a custom command for running prompts with web search enabled and listing the referenced documents.
2023
Introducing Claude 2.1. Anthropic’s Claude used to have the longest token context of any of the major models: 100,000 tokens, which is about 300 pages. Then GPT-4 Turbo came out with 128,000 tokens and Claude lost one of its key differentiators.
Claude is back! Version 2.1, announced today, bumps the token limit up to 200,000—and also adds support for OpenAI-style system prompts, a feature I’ve been really missing.
They also announced tool use, but that’s only available for a very limited set of partners to preview at the moment.
A simple Python implementation of the ReAct pattern for LLMs. I implemented the ReAct pattern (for Reason+Act) described in this paper. It's a pattern where you implement additional actions that an LLM can take - searching Wikipedia or running calculations for example - and then teach it how to request that those actions are run, then feed their results back into the LLM.
The surprising ease and effectiveness of AI in a loop (via) Matt Webb on the langchain Python library and the ReAct design pattern, where you plug additional tools into a language model by teaching it to work in a “Thought... Act... Observation” loop where the Act specifies an action it wishes to take (like searching Wikipedia) and an extra layer of software than carries out that action and feeds back the result as the Observation. Matt points out that the ChatGPT 1/10th price drop makes this kind of model usage enormously more cost effective than it was before.