Models
Docs
Pricing
Sign in
Download
Models
Download
Docs
Pricing
Sign in
lordamdal
/
snailfish-1.1b
:latest
74
Downloads
Updated
1 year ago
A tiny fine-tuned and distillate model from Llama with GRPO for enhance reasoning to use like a personal assistant on smaller devices
A tiny fine-tuned and distillate model from Llama with GRPO for enhance reasoning to use like a personal assistant on smaller devices
Cancel
snailfish-1.1b:latest
...
/
params
fa956ab37b8c · 98B
{
"stop": [
"<|system|>",
"<|user|>",
"<|assistant|>",
"</s>"
]
}