FireFunction from FireworksAI
24 Pulls Updated 7 months ago
Updated 7 months ago
7 months ago
f7cdaad51162 · 26GB
model
archllama
·
parameters46.7B
·
quantizationQ4_0
26GB
template
<s>SYSTEM: {{ .System }}
USER: {{ .Prompt }}
ASSISTANT:
58B
params
{"num_ctx":4096,"num_gpu":-1,"stop":["\u003c/s\u003e"],"temperature":0.1}
74B
system
You are a helpful assistant with access to functions. Use them if required.
FUNCTIONS: [
{
"t
628B
Readme
FireFunction from FireworksAI
A slightly tweaked version of joefamous/firefunction-v1 that lowers temperature a bit and lets Ollama decide what to do with GPU offloading