An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
tools
70b
14.8K Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
3e634098cae4 · 37GB
model
archllama
·
parameters70.6B
·
quantizationQ3_K_L
37GB
params
{"stop":["\u003c|start_header_id|\u003e","\u003c|end_header_id|\u003e","\u003c|eot_id|\u003e"]}
96B
template
{{- if .Messages }}
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
{{ if .Sy
2.0kB
license
META LLAMA 3 COMMUNITY LICENSE AGREEMENT
Meta Llama 3 Version Release Date: April 18, 2024
“Agree
7.8kB
Readme
Firefunction-v2 is competitive with GPT-4o function calling capabilities, scoring 0.81 on a medley public benchmarks vs 0.80 for GPT-4o.
Firefunction-v2 is optimized for real world scenarios including multi-turn conversation, instruction following and parallel function calling. It retains Llama 3’s multi-turn instruction capability (0.84 vs 0.89 on MT bench) while consistently outscoring Llama 3 on function calling tasks (0.51 vs 0.30 on Nexus parallel multi function eval)