A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
tools
8b
70b
41.1K Pulls Updated 5 months ago
Updated 5 months ago
5 months ago
9dc66563ded8 · 4.7GB
model
archllama
·
parameters8.03B
·
quantizationQ4_K_S
4.7GB
params
{
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
96B
template
{{- if .Messages }}
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{ .Syste
1.7kB
license
META LLAMA 3 COMMUNITY LICENSE AGREEMENT – Adapted For Groq 8B/70B Tool Use
Meta Llama 3 Version R
9.8kB
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)