dolphin3-nsfw-gf-chat-gguf – AI Model by jmachine | AlphaNeural AI

You can deploy this model and start earning money today!

jmachine/
dolphin3-nsfw-gf-chat-gguf

like

0

dphn/Dolphin3.0-Llama3.1-8B

endpoints_compatible

not-for-all-audiences

Views

No views yet

dolphin3-nsfw-gf-chat-gguf

GGUF conversion of jmachine/dolphin3-nsfw-gf-chat, a LoRA fine-tune of dphn/Dolphin3.0-Llama3.1-8B on NSFW GF chat data.

Quantizations

File	Format	Size	Notes
dolphin3-nsfw-gf-chat-f16.gguf	F16	~16GB	Full precision
dolphin3-nsfw-gf-chat-q8_0.gguf	Q8_0	~8GB	Near-original quality
dolphin3-nsfw-gf-chat-q5_k_m.gguf	Q5_K_M	~5GB	Good quality
dolphin3-nsfw-gf-chat-q4_k_m.gguf	Q4_K_M	~4GB	Recommended

Usage with Ollama

bash

hf download jmachine/dolphin3-nsfw-gf-chat-gguf dolphin3-nsfw-gf-chat-q4_k_m.gguf
echo "FROM ./dolphin3-nsfw-gf-chat-q4_k_m.gguf" > Modelfile
ollama create nsfw-gf -f Modelfile
ollama run nsfw-gf