Jatin19K/ llamafactory_gemma-2-27b-instruct-q4_k_m:latest

86 1 year ago

QLORA adaptor(q4) trained via Llamafactory from Huggingface's "google/gemma-2-27b-it", then merged(Q4_K_M) with Ollama's "gemma2:27b-instruct-fp16" using Ollama's Modelfile. Adaptor training data: HF's "JatinkInnovision/ShareGPT_Gemma2_it".

... /
template
109037bec39c · 136B
<start_of_turn>user
{{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn>
<start_of_turn>model
{{ .Response }}<end_of_turn>