SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
Paper • 2312.15166 • Published • 61
How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lowendmicrobacteria/highendgirlfriend:Q4_K_M# Run inference directly in the terminal:
llama cli -hf lowendmicrobacteria/highendgirlfriend:Q4_K_MUse pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf lowendmicrobacteria/highendgirlfriend:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf lowendmicrobacteria/highendgirlfriend:Q4_K_MBuild from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf lowendmicrobacteria/highendgirlfriend:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf lowendmicrobacteria/highendgirlfriend:Q4_K_MUse Docker
docker model run hf.co/lowendmicrobacteria/highendgirlfriend:Q4_K_MQuick Links
Perhaps more MidEnd... only 8x122M
Both depth up-scaling (as used in SOLAR) and sparse upcycling are used in this model.
Have fun
- Downloads last month
- 33
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for lowendmicrobacteria/highendgirlfriend
Base model
SupraLabs/Supra-50M-Base Quantized
SupraLabs/Supra-50M-Instruct Finetuned
huggingwadhah/lowendgirlfriend
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf lowendmicrobacteria/highendgirlfriend:Q4_K_M# Run inference directly in the terminal: llama cli -hf lowendmicrobacteria/highendgirlfriend:Q4_K_M