You can deploy this model and start earning money today!

krizk093/
juliana-mistral-7b-q6-gguf

Base: Mistral 7B Instruct v0.3
Format: GGUF Q6_K (~6GB)
Quality: 96-97% of full precision

Name: juliana-mistral-7b-q6-gguf
Availability: InStock

Views

No views yet

Juliana - Mistral 7B Instruct v0.3 (Q6_K GGUF)

Fine-tuned Mistral 7B Instruct model for conversational AI.

koboldcpp --model juliana-mistral-7b-Q6_K.gguf --gpulayers 32 --contextsize 4096

./llama-cli -m juliana-mistral-7b-Q6_K.gguf -n 256 --temp 0.9

Apache 2.0