Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 33
How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/BioMistral-DARE-NS-GGUF:# Run inference directly in the terminal:
llama-cli -hf QuantFactory/BioMistral-DARE-NS-GGUF:Use 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 QuantFactory/BioMistral-DARE-NS-GGUF:# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/BioMistral-DARE-NS-GGUF:Build 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 QuantFactory/BioMistral-DARE-NS-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/BioMistral-DARE-NS-GGUF:Use Docker
docker model run hf.co/QuantFactory/BioMistral-DARE-NS-GGUF:Quick Links
QuantFactory/BioMistral-DARE-NS-GGUF
This is quantized version of BioMistral/BioMistral-DARE-NS created using llama.cpp
Original Model Card
BioMistral-NS
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using Kukedlc/NeuralSynthesis-7B-v0.1 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Kukedlc/NeuralSynthesis-7B-v0.1
parameters:
density: 0.53
weight: 0.4
- model: BioMistral/BioMistral-7B-DARE
parameters:
density: 0.53
weight: 0.3
merge_method: dare_ties
tokenizer_source: union
base_model: Kukedlc/NeuralSynthesis-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
- Downloads last month
- 585
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf QuantFactory/BioMistral-DARE-NS-GGUF:# Run inference directly in the terminal: llama-cli -hf QuantFactory/BioMistral-DARE-NS-GGUF: