A compact, yet powerful 10.7B large language model designed for single-turn conversation.
18K Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
059fdabbe6e6 · 6.1GB
model
archllama
·
parameters11B
·
quantization4-bit
6.1GB
template
### System:
{{ .System }}
### User:
{{ .Prompt }}
### Assistant:
67B
params
{"num_ctx":4096,"stop":["</s>","### System:","### User:","### Assistant:"]}
86B
Readme
Solar is the first open-source 10.7 billion parameter language model. It’s compact, yet remarkably powerful, and demonstrates state-of-the-art performance in models with parameters under 30B.
This model leverages the Llama 2 architecture and employs the Depth Up-Scaling technique, integrating Mistral 7B weights into upscaled layers.
On the H6 benchmark, this model outperforms models with up to 30B parameters, even the Mixtral 8X7B model.