llama3-groq-tool-use

307.4K Downloads Updated 1 year ago

A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.

tools 8b 70b

ollama run llama3-groq-tool-use

curl http://localhost:11434/api/chat \
  -d '{
    "model": "llama3-groq-tool-use",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='llama3-groq-tool-use',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'llama3-groq-tool-use',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model llama3-groq-tool-use

Codex ollama launch codex --model llama3-groq-tool-use

OpenCode ollama launch opencode --model llama3-groq-tool-use

OpenClaw ollama launch openclaw --model llama3-groq-tool-use

Models

View all →

Name

33 models

Size

Context

Input

llama3-groq-tool-use:latest

4.7GB · 8K context window · Text · 1 year ago

llama3-groq-tool-use:latest

4.7GB

Text

llama3-groq-tool-use:8b

latest

4.7GB · 8K context window · Text · 1 year ago

llama3-groq-tool-use:8b latest

4.7GB

Text

llama3-groq-tool-use:70b

40GB · 8K context window · Text · 1 year ago

llama3-groq-tool-use:70b

40GB

Text

Readme

These models, developed in collaboration with Glaive, represent a significant advancement in open-source AI capabilities for tool use/function calling.

Benchmark Results

These models have achieved remarkable results, setting new benchmarks for Large Language Models with tool use capabilities:

Llama-3-Groq-70B-Tool-Use: 90.76% overall accuracy (#1 on BFCL at the time of publishing - July 2024)
Llama-3-Groq-8B-Tool-Use: 89.06% overall accuracy (#3 on BFCL at the time of publishing - July 2024)

References

Hugging Face

Blog